Blog

AI Agents in Focus: From Hermes to OpenClaw – This Week’s Overview

Thursday, May 21, 2026

Hello, this weekly newsletter guides you through the most important new videos from a curated selection of AI and Coding YouTube channels. A compact summary for each video, plus a daily overview of dominant topics. If interested, simply click the link under the summary.

AI with Arnie (5 new videos)

• Codex: ChatGPT with Hands
  17.5.2026, 19:08:45

  **Summary:**

  The video introduces two personal agents, Hermes and OpenCla, and demonstrates their applications and differences from classical agents like Cloud Code and Codex. Various use cases are shown, including stock market research, training and nutrition management, video editing, AI news summaries, real-time monitoring, access to MCD servers, creation of YouTube thumbnails, and managing an entire server. The installation and configuration of Hermes on a virtual private server (VPS) is explained in detail, including connection with GitHub and the use of Superbase for database applications. The video emphasizes Hermes’ self-improvement capabilities and the benefits of OpenCla for tasks requiring continuous monitoring. It also demonstrates the integration of multi-agents and super-agents, as well as the ability to solve complex tasks with the `/goal` command. At the end, a comparison between Hermes and OpenCla is drawn, highlighting their respective strengths and applications.

  **Final Comment:**
  The video explicitly addresses the AI tools Hermes and OpenCla and is intended more for intermediate and advanced users.

• Claude Code is Not Enough Anymore
  15.5.2026, 13:06:39

  The video presents the announcement of Subq (Subquadrantic), a new AI model with a context window of 12 million tokens, representing significant progress over existing models like ChatGPT (1 million tokens). Subq uses a subquadratic sparse attention architecture, enabling linear instead of quadratic scaling, resulting in substantially higher efficiency and lower costs. The model is said to be 52 times faster and cost only 5% of competitors like Opus. The announcement was published on X (formerly Twitter) by Alexander and includes an API for Subq Code and Subq Search.

  The advantages of Subq lie in the ability to keep large codebases or lengthy documentation entirely in context, potentially making current workarounds like RAG (Retrieval-Augmented Generation) or agent workflows unnecessary. The sparse attention architecture allows focusing on only relevant tokens, significantly boosting processing power and speed. However, detailed technical papers are not yet available, and available benchmarks are limited and somewhat controversial.

  Subq’s potential is enormous, as it could revolutionize working with AI in areas such as coding, law, research, and auditing. However, the question remains whether the model can deliver promised quality and reliability with large context windows. Available benchmarks show promising results, but further testing and confirmation are needed.

  The video explicitly addresses the new Subq model and is intended more for intermediate or advanced users engaging with technical details and implications of AI models.

• Is This AI Breakthrough Real?
  7.5.2026, 15:15:00

  The video tests and compares new models from OpenAI, particularly GPT 5.5 and the image model GPT Image 2.0, as well as competition from Deeps version 4. The test covers various applications such as creating a website, simulating a beehive, a 3D motorcycle racing game, an interactive factory and production simulation, traffic simulation, creating ComfyUI and N8N workflows, and analyzing financial data. The benchmarks show that GPT 5.5 demonstrates significant improvements over previous versions in many areas, particularly in the Terminal Benchmark and Vending Benchmark. The video also discusses current issues at Anthropic, especially rate limits, performance problems, and model unreliability, as well as the pros and cons of OpenAI and Anthropic plans. It is recommended not to rely on a single provider and to use both models to balance different strengths and weaknesses.

  The video explicitly addresses OpenAI (GPT 5.5, GPT Image 2.0, Codex), Anthropic (Cloud Code), and Deeps version 4. It is intended more for intermediate and advanced users as it includes detailed tests and technical analyses.

• GPT 5.5 is a Machine
  25.4.2026, 14:03:17

  The video compares AI agents Hermes and OpenCla, focusing on Hermes. Hermes is an open-source project by New Research that stands out for its ability to grow with the user and continuously improve itself. In contrast, OpenCla is an orchestrator that executes tasks and is configuration-oriented. Hermes runs on Python and has persistent memory, while OpenCla runs on TypeScript and uses session-based memory.

  The installation process of Hermes is explained in detail, including the possibility of installing it on various platforms such as Linux, macOS, WSL2, and even Android. Users can install Hermes on a virtual private server (VPS), which has the advantage of making the agent constantly available. Hostinger is mentioned as a convenient provider for Hermes installation.

  After installation, the video shows how to connect Hermes with Telegram and how to use various skills and tools. Hermes can automate tasks, such as monitoring YouTube channels and creating summaries of videos. The agent can also independently create and improve skills without user intervention.

  Another focus of the video is the migration from OpenCla to Hermes. It is recommended to perform the migration gradually and manually, as the memory and skill structures of the two agents differ.

  The video concludes with a discussion on when to use which agent. OpenCla is well-suited for executing many individual tasks, while Hermes is ideal for tasks that improve and adapt over time, such as trading bots or social media managers.

  **AI Tools/Models/Providers:** Hermes Agent, OpenCla, OpenAI, Anthropic, OpenRouter, Hostinger
  **Target Audience:** Intermediate

• Is Hermes the OpenClaw Killer?
  22.4.2026, 08:05:18

  **YouTube Video Summary:**

  The video presents a detailed comparison between AI agents **Hermes** and **OpenCla**, focusing on Hermes’ features, installation, and applications. Hermes is described as an agent that grows with the user and continuously improves, while OpenCla functions more as an orchestrator for task execution.

  **Key Points of the Video:**

  1. **Introduction to Hermes:**
  – Hermes is an open-source project from News Research that already has 100,000 stars on GitHub.
  – It offers a light mode and detailed documentation.
  – Hermes runs on Python and has persistent memory, while OpenCla runs on TypeScript and uses session-based memory.

  2. **Installation and Setup:**
  – Hermes can be installed on Linux, macOS, WSL2, and even Android.
  – Installation on a virtual private server (VPS) is recommended to make the agent available 24/7.
  – The Hostinger provider offers one-click installation for Hermes.

  3. **Features and Comparison with OpenCla:**
  – Hermes has a memory system that persists across sessions, while OpenCla relies on markdown files.
  – Hermes has integrated learning loops and improves itself autonomously, while OpenCla uses manually installed skills.
  – Hermes comes with 30 pre-installed skills ready to use immediately.

  4. **Security and Privacy:**
  – Hermes has a smaller attack surface compared to OpenCla, as it requires fewer external skills.
  – Installation on a separate server is recommended to minimize security risks.

  5. **Practical Applications:**
  – Hermes can be used for various tasks, such as monitoring YouTube channels, creating social media posts, and automating trading strategies.
  – The agent can adapt to the user’s writing style and find relevant information.

  6. **Migration from OpenCla to Hermes:**
  – A complete migration from OpenCla to Hermes can cause problems as the memory and skill structures are different.
  – It is recommended to migrate and test skills and memory files manually.

  7. **Summary and Recommendations:**
  – Hermes is particularly suitable for tasks that improve over time, such as trading bots or social media managers.
  – OpenCla is better suited for orchestrating individual tasks.
  – Both agents can be combined to leverage the advantages of both systems.

  **Final Comment:**
  The video explicitly addresses the AI agents **Hermes** and **OpenCla** and is intended more for **Intermediate** users who already have experience with AI tools and wish to deepen their knowledge.

Cole Medin (10 new videos)

• Pushing My AI Dark Factory to Its Limits with Opus + Kimi Combined
  19.5.2026, 03:35:08

  The video shows a detailed exploration and demonstration of the coding agent Pi. The focus is on presenting Pi as a minimal, customizable coding agent that can be tailored to individual user workflows. The user integrates Pi with Archon, an open-source tool for creating harnesses, and shows how Pi can be used with various models like Kimmy, Miniax, and Opus.

  Key steps and insights from the video include:

  1. **Setting up Pi with Kimmy**: The user demonstrates how to configure Pi to work with a Kimmy code subscription instead of Codeex. The steps for API key setup and integration into Pi’s configuration are explained in detail.

  2. **Installation and use of extensions**: The user installs and tests various extensions from the Pi marketplace, including an extension for subagents, a web access extension, and an extension for managing Archon workflows. These extensions enable additional features like desktop notifications, status bars, and integration of Archon workflows.

  3. **Creating a custom extension**: The user creates a custom extension called “Archon Dispatch” that transforms Pi into a control panel for Archon background tasks. This extension enables the execution of Archon workflows, display of live status information, and notifications when workflows complete.

  4. **Issues and solutions**: During the demonstration, some problems arise, particularly with the integration of Archon workflows and the display of workflow results in Pi. The user attempts to resolve these issues with Kimmy but encounters limitations in model capabilities. He discusses the benefits of combining stronger models like Opus with cheaper models like Kimmy to achieve the best results.

  5. **Comparison with other tools**: The user compares Pi with other coding agents like Codeex and Claude Code and highlights Pi’s advantages, particularly its customizability and speed.

  6. **Future plans**: The user plans to continue working on the integration of Pi and Archon in future live streams and videos, and potentially develop an Archon workflow for creating Pi extensions.

  The video explicitly discusses AI tools and models Claude, Codeex, Kimmy, Miniax, Opus, and Open Router. It is aimed at intermediate and advanced users interested in customizing and integrating coding agents.

• Pi is INCREDIBLE – Building a Custom Coding Agent Live
  17.5.2026, 03:42:53

  **Summary:**

  In this stream, the new workflow marketplace for Archon was introduced and two community workflows were added. The first workflow, “Idea to Work Order”, helps convert ideas into detailed work orders for development. The second workflow, “Archon SmartMR Review”, is a GitLab equivalent to the pull request review workflow.

  The workflow integration process was demonstrated live, including creating a pull request, automatic review by GitHub Action, and subsequent release. Technical challenges and improvements were also discussed, such as updating the Archon CLI and notifying about available updates.

  **Final comment:**

  The video discusses the use of Claude (OpenAI) and specific tools like Archon. It is aimed at intermediate and advanced users.

• 🔴 The AI Coding Marketplace is Finally LIVE!
  15.5.2026, 03:17:26

  The video demonstrates how to create fully animated videos with audio using AI. The process utilizes multiple technologies, including HyperFrames for rendering, Claude Code for control, 11Labs or Kokoro for speech generation, and Archon as a workflow manager. The creator provides an open-source repository that enables creating AI-generated videos in less than 10 minutes. The workflow includes scripting, audio creation, visual rendering, and synchronizing all elements. The creator emphasizes that while the technology isn’t perfect yet, it’s rapidly advancing and already finding useful applications, particularly for explainer videos. The process is explained in detail, including the ability to customize templates and create custom ones. At the end, examples of generated videos are shown.

  The video explicitly discusses HyperFrames, Claude Code, 11Labs, Kokoro, and Archon and is aimed at intermediate users.

• Make the PERFECT Videos with Claude Code (Full Workflow)
  14.5.2026, 00:00:24

  **Summary:**

  In this live stream, the development of a workflow marketplace for Archon, an open-source harness builder for AI coding, continued. The focus was on creating a marketplace where users can share their own workflows and utilize workflows from others. The process included creating an Archon workflow that automatically reviews and approves pull requests for new workflows. The stream began with merging an existing pull request that introduced the marketplace UI and continued with creating a new workflow that reviews pull requests.

  The process involved multiple steps, including creating a plan, implementing the plan, and reviewing generated code. Various questions and adjustments were discussed to ensure the workflow functions correctly. The stream concluded with creating a pull request for a test workflow and demonstrating how the automatic review process works.

  **Final comment:**
  The video explicitly discusses the use of Claude (Claude Code) and is aimed at intermediate to advanced users.

• Building the App Store for Agentic Engineering
  12.5.2026, 04:02:35

  **YouTube Video Summary:**

  The video presents a live demo of the AI tool Archon, developed as an open-source harness builder for AI coding. The streamer showcases his current AI coding workflow and how Archon accelerates this process tenfold. He demonstrates Archon’s use for various tasks, including handling GitHub issues (brownfield development) and creating new features (greenfield development).

  1. **Brownfield Development:**
  – The streamer shows how he uses Archon to handle multiple GitHub issues in parallel. Workflows are used that include planning, implementation, and validation.
  – Workflows are designed to create comprehensive pull requests that can then be manually reviewed.
  – It’s demonstrated how Archon integrates with a “Second Brain” (a system for organizing knowledge and tasks) to optimize the workflow.

  2. **Greenfield Development:**
  – The streamer plans and implements a new feature for Archon: a workflow marketplace that enables users to create and share their own workflows.
  – The PIV-Loop (Plan, Implement, Validate) is used, a structured approach to AI-powered development encompassing planning, implementation, and validation.
  – It’s shown how Archon workflows can be used for complex tasks such as creating a new marketplace feature.

  3. **Technical Details:**
  – Archon enables creating workflows that can integrate various AI models and tools, including Claude, Codex, and others.
  – Workflows are designed to be deterministic and repeatable, enhancing reliability and efficiency.
  – The streamer emphasizes the importance of human-in-the-loop processes to ensure result quality.

  4. **Integration and Extensions:**
  – It’s demonstrated how Archon can be integrated with other tools like Beads (a memory system).
  – The streamer discusses Archon’s advantages compared to other tools like N8N and emphasizes Archon’s specialization in AI coding.

  5. **Community and Further Development:**
  – The streamer mentions the Dynamis community, where he regularly offers workshops and courses to help users effectively use Archon and other AI tools.
  – He announces that he will continue conducting live streams to demonstrate Archon’s development and use.

  **Concluding Comment:**
  The video explicitly discusses the tool Archon and is aimed at intermediate to advanced users interested in AI coding and workflow automation.

• 🔴LIVE – My AI Coding Workflow has 10x’d Again with Archon – See it in Action
  10.5.2026, 05:56:02

  The YouTuber expresses his frustration with the current YouTube landscape, which heavily focuses on reporting Claude and its latest features. He wants to stand out from the crowd and instead offer deeper, more technical content focused on actually building and the principles of AI coding. To do this, he plans to conduct live streams three times a week (Monday, Thursday, Saturday) showcasing projects like Archon and the Dark Factory experiment while working interactively with the community. He emphasizes that he will continue to cover relevant AI news but with a focus on practical application and long-term value. The content is aimed at intermediate and advanced users interested in AI coding and systems. The YouTuber explicitly discusses Claude and Claude Code.

• AI YouTube Is Only Claude Hype Now
  7.5.2026, 00:01:02

  **Summary:**

  In the video, the creation of a roadmap for the open-source project Archon, a harness builder for AI coding, is presented live. The host begins with an introduction to Archon, which enables packaging AI coding processes into workflows and executing them in parallel across various codebases. Workflows are defined in YAML and can include both agent-based and script-based actions.

  A central theme is the idea of a marketplace for Archon workflows, which should enable users to share and install their own workflows. The host discusses various approaches for implementing this marketplace, including whether workflows should be hosted in separate repositories or integrated directly into the Archon repository. The pros and cons of both approaches are discussed, with security and user-friendliness being the focus.

  During the video, the current Archon roadmap is also created and updated, with various features and improvements being added, such as support for the PI coding agent and optimization of the setup process. The host uses Cloud Code and other tools to visualize and refine the roadmap.

  **Concluding Comment:**

  The video explicitly discusses open-source tools and models, particularly Claude and Cloud Code, and is aimed at intermediate to advanced users.

• 🔴LIVE – What’s Next for Archon – Live Roadmap Session
  5.5.2026, 03:58:13

  **YouTube Video Summary:**

  The video shows the creation of AI-generated videos using Archon, an open-source harness builder. The process involves using Archon for the workflow, 11 Labs for voice generation, and Remotion for video generation. The creator demonstrates creating a video about the new TI-84 EVO calculator and subsequently explains the steps for creating a marketing video for Archon itself.

  **Steps and Tools:**
  1. **Archon Workflow:**
  – Archon is used to create a workflow that divides video generation into multiple steps.
  – The workflow includes planning the video, generating audio and video, validating, and iterating.

  2. **11 Labs for Voice Generation:**
  – 11 Labs is used to generate voice output.
  – The creator experiments with various parameters such as speed, stability, similarity, and style exaggeration to achieve the best sound quality.

  3. **Remotion for Video Generation:**
  – Remotion is used to create the visual elements of the video.
  – The creator shows how the workflow plans and generates various scenes and animations.

  4. **Iteration and Improvement:**
  – The creator demonstrates how to iteratively improve the generated video by providing feedback and adjusting the workflow.
  – It’s shown how to enhance voice output and sound effects.

  5. **Archon Workflow Details:**
  – The workflow is defined in a YAML file and includes multiple steps orchestrated by Archon.
  – Each step can use different models and providers, which increases workflow flexibility and reliability.

  **Concluding Comment:**
  The video explicitly discusses Archon, 11 Labs, Remotion, and open-source models. It is aimed at intermediate and advanced users familiar with AI tools and workflows.

• Anthropic Just Dropped a Masterclass on Building Agent Harnesses (for Large Codebases)
  21.5.2026, 00:00:30

  The video addresses strategies for effectively using Claude Code with large and complex codebases. It begins by noting that many tutorials focus on simple code examples while working with large codebases is often neglected. The author presents ideas from a blog post by Anthropic that addresses the use of Claude Code in large codebases. The main thesis is that the “harness” (environment and tools) is just as important as the underlying model.

  Key strategies include:
  1. **Global Rules**: These should be lean and layered to help Claude Code navigate different parts of the codebase. It’s recommended to have global rules in subdirectories to provide context-specific instructions.
  2. **Hooks**: These can be used to make the entire AI environment self-improving. Start hooks can load context-specific information, while stop hooks can suggest updates to global rules.
  3. **Skills**: These are reusable prompts or processes that are only loaded when needed. They can be restricted to specific paths in the codebase to reduce context size.
  4. **Language Server Protocol (LSP) and MCP Servers**: These enable Claude Code to use the same navigation as a developer in their IDE. This is particularly useful for large codebases as it enables more targeted searches.
  5. **Subagents**: These can be used for exploratory tasks to avoid overwhelming the context window of the main session. They perform analyses and return a summary.

  The author also demonstrates a plugin that integrates some of these strategies into a demo codebase to facilitate implementation. He emphasizes the importance of actively maintaining and improving the AI environment (AI layer) to increase Claude Code’s effectiveness.

  The video explicitly discusses Claude Code and is aimed at intermediate to advanced users who already have experience working with larger codebases.

• Plan with Claude Opus, Build with Kimi K2.6? LIVE Mixed-Provider Benchmark
  20.5.2026, 22:52:56

  The video is a summary of major news from the world of artificial intelligence. Several stories are covered, including the latest version of OpenAI’s language model, which offers improved text generation capabilities. Additionally, reporting covers a new open-source initiative that enables developers to train their own AI models. Another topic is the introduction of a new tool that simplifies the integration of AI into existing enterprise software. The video also discusses the ethical implications of these developments and emphasizes the importance of transparency and accountability in AI research.

  Concluding Comment: The video discusses OpenAI and open-source tools and is aimed at intermediate and advanced users.

Nate Herk | AI Automation (10 new videos)

• What Karpathy Joining Anthropic Actually Means For Claude
  19.5.2026, 21:36:51

  The video discusses the significance of Andre Karpathy joining Anthropic and analyzes why this move is of great importance for both Karpathy and Anthropic. Karpathy, a central figure in the modern AI world, has an impressive career behind him, including his role as co-founder of OpenAI and his work at Tesla. His recent projects, such as Eureka Labs and the development of concepts like “Vibe Coding” and “Context Engineering,” demonstrate his ability not only to develop AI but also to teach how to use it effectively.

  Anthropic has made significant progress recently, particularly with Claude Code, which has become a popular tool for developers and businesses. Karpathy’s arrival could suggest that Anthropic is expanding its strategy further by improving not just AI models, but also their applications and integration into real-world workflows. Karpathy’s focus on “Context Engineering” and creating environments that enable AI models to work more effectively aligns well with Anthropic’s approach.

  The video makes three predictions: First, that Anthropic will develop an app store for contexts and workflows. Second, that there will be more features like “/goal” that enable complex tasks to be handled automatically. Third, that Anthropic will create an educational platform to help users package and contribute their own workflows.

  The video explicitly covers Claude / Anthropic and is geared more toward Intermediate and Advanced users.

• How to Use Your Claude Code Projects in Codex in 5 Mins
  18.5.2026, 19:09:24

  The video shows how to migrate a project from Claude Code to Codex without duplicating it or losing important information. The main difference between the two tools lies in file names and folder structures: Claude Code uses a `cloud.md` file and a `cloud` folder, while Codex uses an `agents.md` file and a `codex` folder as well as an `agents` folder for skills. However, both tools share the same knowledge base such as documents, references, and scripts.

  The author explains that you can use a simple prompt to instruct Codex to create the necessary files and folders and adopt the contents from the Claude Code files. It’s important to note that changes in Claude Code files must also be made in Codex files to ensure consistency. Additionally, the author points out that Codex subagents are not called automatically and there are some differences in tools and commands.

  A practical example shows how Claude Code and Codex can work together to create and style an HTML document. The author recommends using both tools and not limiting yourself to a single tool to remain flexible.

  Closing comment: The video explicitly covers Claude Code and Codex tools and is geared more toward Intermediate users.

• The AI Career Opportunity Nobody is Talking About in 2026
  17.5.2026, 16:24:10

  Video creator Nate discusses an alternative career option in the AI field, aside from the often-promoted model of founding an AI automation agency. He argues that many companies, particularly large corporations, are increasingly hiring Chief AI Officers (CAIOs) or have already done so, and that this represents a great opportunity for people who don’t want to work in sales. Nate references an IBM study showing that 76% of surveyed CEOs either already have a CAIO or want to hire one, representing an enormous increase compared to previous years. He explains that the CAIO role emerged similarly to the Chief Information Security Officer (CISO) role, to address a new, urgent need in companies.

  Nate emphasizes that it’s not just the CAIO role, but that every department in companies is looking for AI-savvy executives. He presents two paths to pursue this direction: Path A, where you start as an AI consultant or in an agency and then get acquired by a company, and Path B, where you build AI skills internally in your current job and qualify for promotion. He argues that Path B might be more accessible to many people, as 57% of CAIOs were promoted internally.

  Nate emphasizes the importance of loving what you do, since otherwise you won’t have the necessary endurance and motivation to succeed in this field. He encourages viewers to become the AI-native version of their current role rather than jumping into a new field that doesn’t suit them. He concludes by stating that you don’t need to change your role, but rather the version of your role that you perform.

  The video explicitly covers IBM and their studies as well as the role of Chief AI Officer in companies. It is more suitable for Intermediate and Advanced users, as it builds on solid knowledge and experience in the AI field.

• How to Deploy Your Claude Automations (3 Methods)
  15.5.2026, 15:16:02

  The video explains three methods to deploy agents from Anthropic’s Claude Code environment so that they run even when the user is not actively present. The methods are compared using a schema that answers the question of where the agent runs (locally or in the cloud) and how autonomous/agentic it operates.

  1. **Loops:**
  – Simple method where Claude Code is instructed to create a loop that runs a specific task at regular intervals (e.g., every 10 minutes).
  – Uses internal tools like `cron create`, `cron list`, and `cron delete` for scheduling.
  – The loops are session-specific and run either in the desktop app or in the terminal.
  – **Advantages:** No additional setup needed, full agent functionality within the session.
  – **Disadvantages:** The session and computer must be running, maximum runtime of 7 days, fixed intervals with random delay (jitter).

  2. **Desktop Scheduled Tasks and Cloud Routines:**
  – **Desktop Scheduled Tasks:** Run locally on the computer and require the desktop app to remain open.
  – **Cloud Routines:** Run in Anthropic’s cloud and don’t require an active session or running computer.
  – Both methods inject a prompt into a Claude Code session and execute the task.
  – **Advantages:** No additional infrastructure needed, full Claude Code functionality, Cloud Routines can also be triggered via API or GitHub events.
  – **Disadvantages:** Cloud Routines have a minimum of 1 hour between executions, limited number of executions per day (depending on plan).

  3. **Deployment on Modal or Trigger.dev:**
  – Here a script (Python for Modal, TypeScript for Trigger.dev) is deployed to the respective cloud platform and runs there on a schedule or as an API endpoint.
  – **Advantages:** No need to keep your own computer or a session running, good for deterministic processes.
  – **Disadvantages:** No full agent functionality, AI processing occurs via API and is thus more expensive. With Claude’s Agent SDK you can also use agentic functions, but this is also more expensive.

  Additionally, **Managed Agents** from Anthropic and **Hooks** in Claude Code are briefly mentioned, which can be used for event-driven automations.

  The video is more suitable for **Intermediate** users who already have experience with Claude Code and agents. It covers specific tools and providers including **Claude (Anthropic)**, **Modal**, **Trigger.dev**, and the **Claude Agent SDK**.

• Anthropic Just Dethroned OpenAI. Here’s What Happens Next.
  13.5.2026, 21:20:51

  The video discusses the current dynamics in AI-powered coding tools, particularly the competition between OpenAI (Codex) and Anthropic (Claude Code). It begins with the observation that Anthropic has surpassed OpenAI in business use, followed by OpenAI’s response offering companies two months of free Codex usage. Claude Code responded with a 50% increase in weekly usage limits for the next two months. The author interprets these moves as part of a “free trial phase” in which companies and users use the tools intensively while providers aim for adoption and data collection. It’s argued that current prices are not sustainable and users ultimately provide valuable training data for the AI models. The author advises using current offers to avoid dependencies and remain flexible to possible future changes. Historical patterns are also referenced where similar dynamics in other industries led to price increases. The closing comment emphasizes that users should use the tools to avoid becoming locked into a single provider.

  **AI Tools/Models/Providers:** OpenAI (Codex), Anthropic (Claude Code); **Target Audience:** Intermediate to Advanced.

• Every Level of Claude Explained in 21 Minutes
  12.5.2026, 13:59:35

  The video provides a detailed guide on using Claude at five ascending levels: Enthusiast, Beginner, Intermediate, Advanced, and Architect. Each level is defined by specific features and strategies that gradually lead the user from basic applications to complex automations.

  – **Level 1: Enthusiast** – Basic use of Claude for simple tasks like writing emails or explaining content. An important tip is using screenshots, as Claude can read images.
  – **Level 2: Beginner** – Introduction to Projects, which provide context and continuity. Key features include Memory, Connectors (integration with tools like Slack or Google Drive), File Creation (creating Excel files, PowerPoint presentations, etc.), Artifacts (interactive applications), Inline Visuals (visual representations within chats), and Office Add-ins (integration with Microsoft Office).
  – **Level 3: Intermediate** – Use of Claude Co-work for tasks on your own computer. Key features include File System Access, Skills (reusable workflows), Scheduled Tasks (planned tasks), Mobile Control (smartphone control), Cloud Design (design of prototypes and presentations), as well as Plugins and Computer Use (navigation in apps).
  – **Level 4: Advanced** – Use of Claude Code for complex automations and parallel work processes. Key features include the use of claude.md (configuration file), Plan Mode (task planning and execution), Sub Agents (specialized agents), Work Trees (isolated work areas), MCP (Model Context Protocol for tool integration), as well as various optimization techniques and Custom Commands.
  – **Level 5: Architect** – Creation of fully autonomous systems that work without user interaction. Key features include Cloud Routines (planned tasks in the cloud), Hooks (security-related logic), Channels (control of external platforms), Headless Mode (autonomous task execution), Agent SDK (creation of your own products), and Remote Control (remote control of sessions).

  The video emphasizes that the transition to the highest level is less technical than a matter of trust in the systems. It’s recommended to start with simple, low-stakes automations and gradually implement more complex systems.

  **Closing Comment:** The video explicitly covers Claude and is geared more toward Intermediate to Advanced users.

• Claude Code Just Got an Agent Dashboard
  12.5.2026, 01:06:06

  The video introduces the new “Agent View” feature of Claude Code, which allows managing multiple agent sessions in a single terminal tab. The user can switch between sessions, monitor their status (e.g., “waiting for input,” “completed”), and navigate directly in and out of the sessions. This is particularly helpful for developers who previously struggled with many open terminal tabs and cluttered sessions. Control is via arrow keys or by clicking, and new sessions can be started via simple commands or direct task descriptions. The video also mentions the new “Goal” feature, which allows you to set Claude Code long-term goals that are then pursued autonomously. The video also shows how to delete sessions or provide input directly from the Agent View. At the end, there’s a reference to a course showing how to use Claude Code as your own operating system.

  The video explicitly covers Claude Code and is geared more toward Intermediate or Advanced users who already have experience using Claude Code or similar tools.

• Hermes Agent: Zero to Personal AI Assistant (1 Hour Course)
  10.5.2026, 02:42:25

  The video is a tutorial on setting up and using Hermes Agent, a powerful open-source AI agent from Noose Research. The creator guides viewers through the entire process, from installation on a VPS (Virtual Private Server) to configuration and use of the agent. Here are the main steps and the end result:

  1. **Introduction to Hermes Agent**:
  – Hermes Agent is a self-improving AI agent that grows and adapts with the user.
  – The agent has 684 skills, 91 of which are pre-installed.
  – The agent can automate various tasks, such as generating Excel diagrams, transcriptions, and answering questions.

  2. **Comparison with Other Agents**:
  – Comparison of Hermes Agent with Claude Code and OpenClaw.
  – Hermes Agent is lighter, faster, and focused on self-improvement.
  – Claude Code is primarily used for knowledge work and coding, while Hermes Agent is used for automation and task management on the go.

  3. **Installation and Setup**:
  – The creator shows how to install Hermes Agent on a VPS at Hostinger.
  – A step-by-step guide is provided, including setting up a Telegram bot to interact with the agent.
  – The creator emphasizes the importance of security and shows how to manage API keys securely.

  4. **Using Hermes Agent**:
  – The creator demonstrates how to use the agent for various tasks, such as creating videos with Hyperframes and automating daily tasks.
  – Shows how to sync the agent with a GitHub repo to create backups and save work.

  5. **Self-Improvement Loop**:
  – The creator explains the self-improvement loop of Hermes Agent, where the agent learns from experiences and continuously improves.
  – Emphasizes that users should correct the agent and provide feedback to improve accuracy and efficiency.

  6. **Advanced Features and Tips**:
  – The creator provides tips on using the agent, such as creating skills and automating tasks with Cron jobs.
  – Shows how to use the agent for various tasks and projects, such as managing YouTube comments and creating reports.

  7. **Scaling and Managing Multiple Agents**:
  – The creator discusses scaling and managing multiple Hermes Agents on a VPS.
  – Explains how to host agents in different containers and how to make them communicate with each other.

  8. **Resources and Community**:
  – The creator offers a free resource guide containing all steps and information from the video.
  – References the creator’s free training community where additional resources and documents are available.

  **Closing Comment**: The video explicitly covers Hermes Agent, OpenAI, and specific tools such as Hostinger and GitHub. It is geared more toward Intermediate and Advanced users who already have experience using AI agents and managing servers.

• This is The Most Powerful Tool to Give to Claude Code
  9.5.2026, 01:55:16

  The video introduces the tool **Printing Press**, a CLI factory and library that enables you to create and use efficient command-line interfaces (CLIs) for various services. The speaker demonstrates how CLIs offer advantages over APIs and MCPs (Multi-Tool Chains), particularly in terms of token efficiency and integration into agent workflows. Printing Press provides a library with over 50 pre-built CLIs and a factory for creating custom CLIs. The speaker shows how he created a CLI for a school community without an API in just a few minutes and explains the advantages of CLIs over APIs and MCPs, such as lower token usage and better integration into agent workflows. He also demonstrates how to use pre-built CLIs from the library, such as for ESPN to retrieve NBA games, and how to create custom CLIs, such as for Hacker News. The speaker emphasizes that CLIs are the best option for agents, followed by APIs and then MCPs. He also shows how to share created CLIs with the team by hosting them in a private GitHub repository. In closing, he emphasizes the importance of CLIs for efficient agent use and the possibility of converting almost anything into a CLI.

  The video explicitly covers the **Printing Press** tool and is designed for **Intermediate** users who already have experience with APIs and agent workflows.

• Overwhelmed By AI? Just Copy My Tech Stack
  8.5.2026, 01:38:26

  The YouTuber presents his personal selection of AI tools that he uses daily, weekly, or occasionally, and shares his thoughts on how to handle rapid development and the abundance of new tools without feeling overwhelmed. He begins with his “daily drivers” (S-Tier), including Claude Code (his main tool), VS Code (as an IDE for Claude Code), and Glydo (for speech-to-text transcription). In A-Tier, he mentions tools he uses weekly, such as Codex (another agent tool), Claude (for chat-based tasks), Hermes Agent (for general knowledge work), Perplexity (for research), and Groq (for specific search tasks). He emphasizes that his core stack consists of these few tools, although there are many other tools he uses occasionally or for specific tasks. The YouTuber also discusses his “specialists” (B-Tier), which he uses for particular tasks, such as Appify, GBT Image 2, Nano Banana 2, Key.ai, and HeyGen. In C-Tier, he mentions tools he uses experimentally, such as Gemini, Anti-Gravity, Ollama, and Manifold. He also has a “graduated” category for tools he no longer uses, such as ChatGPT, Open Claw, Cursor, Notebook LM, Poppy AI, Anytten, and WhisperFlow. The YouTuber shares his thoughts on efficiency and productivity, emphasizes the importance of focusing on what matters and not being distracted by new tools. He advises treating tools as “harnesses” that can be integrated into existing projects and emphasizes the importance of focusing on your own goals (North Star) and only using tools that truly add value.

  The video explicitly covers multiple AI tools and models, including Claude Code, VS Code, Glydo, Codex, Claude, Hermes Agent, Perplexity, Groq, Appify, GBT Image 2, Nano Banana 2, Key.ai, HeyGen, Eleven Labs, Cloud Design, Gemini, Anti-Gravity, Ollama, Manifold, ChatGPT, Open Claw, Cursor, Notebook LM, Poppy AI, Anytten, and WhisperFlow. The video is geared more toward Intermediate and Advanced users who already have experience with AI tools and want to optimize their workflows.

Ben AI (5 new videos)

• Every Claude Cowork Feature Explained for Normal People
  20.5.2026, 10:06:05

  The video provides a comprehensive introduction to using Claude Cowork, a tool that can revolutionize the way you and your team work. It starts with an explanation of fundamental concepts and features, divided into three main categories: Memory and Context Concepts, Capabilities and Automation Concepts, and Connectors and MCP Concepts. The focus is on how these concepts can improve efficiency and relevance when working with Claude.

  A central topic is managing Claude’s limited context windows, which are partially addressed through features like global instructions and built-in memory. Users are encouraged to leverage external files and folders to create persistent context, enabled by features like file access and the creation of Clot.MD files. Projects and a centralized “Second Brain” or AIOS (Artificial Intelligence Operating System) are presented as solutions for organizing and accessing context across different projects and teams.

  Claude Cowork’s capabilities, such as code execution, Skills, Skills 2.0, and Evals, as well as scheduled tasks and routines, are explained in detail. These capabilities enable automation of repetitive tasks and more efficient handling of complex work. Connectors and MCP (Model Context Protocol) are presented as means to connect Claude with external software applications, enabling workflow automation across various tools.

  The video concludes with best practices for using Claude Cowork, including selecting the right model for different tasks, optimizing token usage, and deciding when to switch to Claude Code. Tips are also provided for introducing Claude Cowork to a team, including managing permissions and leveraging shared Skills and plugins.

  The video explicitly covers Claude and is better suited for intermediate to advanced users.

• 5 Skills to Build an AI Operating System Like The 1% (Full Guide)
  16.5.2026, 08:48:55

  The video shows how to set up a “Second Brain” or an AI operating system to boost efficiency and productivity with AI tools. The author, Ben, emphasizes the importance of a well-structured and maintained system to optimize token costs and provide relevant context. He introduces five Clot Skills that help set up the system quickly and according to best practices:

  1. **OS Setup Skill**: Assists with initial setup of the Second Brain, including populating context, structuring folders, and creating Clot.md files that serve as an instruction layer for AI agents.

  2. **OS Operator Skill**: Sets up a scheduled task that pulls real-time context from various sources (e.g., meetings, Slack chats) and updates the Second Brain accordingly. This includes creating daily summaries, task lists, and maintaining existing files.

  3. **OS Optimizer Skill**: Conducts regular audits and optimizations to improve the efficiency and token usage of the Second Brain. This includes removing duplicates, correcting formatting, and improving folder structure.

  4. **Team OS Skill**: Enables shared use and synchronization of the Second Brain within a team, including setting up read and write permissions for different team members.

  5. **OS MCP Skill**: Creates an MCP (Managed Connector Proxy) from the Second Brain so that scheduled tasks and optimizations can run autonomously, even with your laptop closed.

  The author recommends starting with setting up the Second Brain and gradually expanding it, as the benefits grow over time with increasing context. He offers additional resources and support for those who want to dive deeper into the topic.

  The video explicitly covers Claude and is better suited for intermediate and advanced users.

• How to Actually Use Claude Design Like a Pro (Real Use Cases)
  12.5.2026, 07:40:42

  The video demonstrates how to efficiently use Claude Design for various design tasks, including presentations, social media content, and websites. The main focus is on a four-step process: First, setting up a comprehensive design system containing colors, fonts, and styles. Second, using templates to predetermine formats and layouts. Third, using Skills to predefine text and content. Fourth, integrating these elements into Claude Design to quickly create consistent designs. The creator emphasizes that this preparation avoids endless iterations and high token costs. Concrete examples and steps for setting up design systems and templates are shown, along with using Skills to automate the process. Free resources and tools are also offered to make getting started easier.

  The video explicitly covers Claude Design and is better suited for intermediate users who already have some experience with AI tools.

• Live Artifacts Just 10x’d Claude Cowork (Real Use Cases)
  27.4.2026, 11:02:09

  The video showcases Claude’s new Live Artifacts feature, which enables creating personalized dashboards with real-time data from various software tools. The creator shares examples of dashboards he’s built for different business areas, such as marketing, sales, customer support, and competitive analysis. These dashboards pull data from tools like YouTube, Bitly, PostHog, Stripe, and Circle to deliver personalized insights and strategic recommendations. Additionally, users can ask questions about the data through an integrated AI chat function, and in some cases, execute direct actions such as composing and sending messages.

  The benefits of Live Artifacts lie in the centralized display of data from multiple sources, dashboard personalization, and the ability to integrate AI-powered insights and actions. The creator emphasizes that this feature has the potential to fundamentally change how work is organized and executed by serving as a central interface for data visualization and automation.

  Current limitations include limited capability to execute actions, inability to share dashboards with others, and performance issues when using multiple connectors. The creator shows how to create Live Artifacts by clearly communicating to Claude what data is needed and what actions the AI should perform. He recommends converting existing scheduled tasks into Live Artifacts to boost efficiency.

  Final note: The video explicitly covers Claude and is intended for intermediate to advanced users.

• How to Use Claude Routines Better than 99% of People
  25.4.2026, 09:12:01

  The video explains Claude’s new Routines feature, which enables automating recurring tasks without requiring technical expertise. Three main examples of Routines are shown: a daily check for failed customer payments, creating personalized offers after a sales call, and a churn recovery routine. Routines can be triggered either on schedule or by events and run autonomously in the cloud. Building a routine consists of four elements: prompt, trigger, repo and files, and connectors. Current limitations of Routines are also discussed, such as the limited number of webhook triggers and the need to store files and Skills in a GitHub repository. The creator shows how to set up a routine from scratch, including setting up a GitHub repository and using N8N to trigger the routine on a specific event. It’s emphasized that creating reliable Routines requires prior creation and testing of Skills.

  The video explicitly covers Claude, GitHub, and N8N and is intended for intermediate users.

Brian Casel (10 New Videos)

• You don’t need to learn to code anymore
  18.5.2026, 13:30:40

  The video demonstrates how to create applications without programming knowledge by using AI as a tool. The focus is on “spec-driven development,” where a clear specification (PRD) is created and then divided into milestones implemented by an AI-coding agent. The process starts with a rough idea that is transformed into a detailed product requirements document (PRD). This document contains all relevant information such as scope, data model, integrations, and features. Subsequently, the PRD is divided into milestones, each representing a completable unit. The creator demonstrates the creation of an invoicing application using two self-developed tools: “build new” as a starter template and “PRD Creator” as an agent skill that supports the PRD creation and milestone breakdown process. The PRD Creator asks questions an experienced product designer would ask, helping to account for all important details. In the end, you have a clear, written planning document that serves as the foundation for implementation by the AI-coding agent.

  The video explicitly covers AI models Claude, Codex, and Gemini, as well as tools Cursor and Resend. It is better suited for intermediate and advanced users, as it assumes viewers already have basic knowledge of using AI tools.

• How I build agents that work the night shift
  12.5.2026, 12:01:07

  The video demonstrates a process the user calls “Radar Scan,” in which multiple AI agents are operated on a Mac Mini with OpenClaw. One of these agents, named Veil, is responsible for marketing and performs a daily Radar Scan at 4:00 AM. The result is saved as a markdown file in Dropbox and can be accessed via a link in Telegram. The file is opened in a custom-built app called Brainown, which simplifies reading and writing markdown files. The scan primarily summarizes tweets from the user’s industry that they follow, including messages from companies, influencers, and thought leaders. The user organizes their Telegram contacts into human and agent friends and receives a report overview in Telegram, with the option to open the full file in Brainown.

  The user discusses OpenClaw and the custom-built app Brainown, making this video particularly interesting for intermediate or advanced users.

• Why You Need Claude Code Server Mode?
  6.5.2026, 14:01:40

  The video illustrates Brian Casel’s workflow evolution with AI agents from 2023 to 2026. Initially he worked manually, from 2024 he used AI as an extension (e.g., tab completion, chatbots for text), in 2025 AI became a collaborator (specifically Claude Code), and in 2026 he orchestrates multiple agents simultaneously. He emphasizes that the quality of specifications (specs) for agents is crucial and that multitasking with agents is now a natural step. The video demonstrates various tools such as Cursor, Claude Code, Superset, and Conductor suitable for agent-based development, with Superset currently being his favorite. He shows how he switches between different worktrees and projects and uses agents on mobile to delegate tasks while pursuing other activities. Additionally, he integrates agents into internal tools like Spark Drop and Brain Down to connect product development and marketing. He uses OpenClaw and Claude Co-Work for automated, recurring tasks. The video concludes by emphasizing that multitasking with agents is the next logical step for builders.

  Final note: The video covers Claude (specifically Claude Code and Opus), OpenClaw, and tools like Cursor, Superset, Conductor. It targets intermediate and advanced builders who already have experience with AI agents.

• Why Every AI Coding Tool is Converging on Plan Mode?
  1.5.2026, 14:01:11

  The video covers setting up OpenClaw, a tool for agent teams, and deciding between a cloud VPS or a physical device. The author explains that he chose a new Mac Mini M4, despite cheaper options like a cloud VPS starting at five dollars per month. His reasons for this choice are the possibility of screen sharing, visual management, and future requirements for storage and bandwidth. If OpenClaw doesn’t meet expectations, the author plans to use the Mac Mini in his home studio.

  The video discusses OpenClaw and is intended for intermediate or advanced users familiar with agent teams and server setups.

• Building a Custom AI News Agent with RSS and Telegram
  29.4.2026, 14:00:14

  The video shows how to create a new GitHub repository via the mobile website and then connect it with the Claude app to generate simple “Hello World” code. The process begins with creating a new repository on GitHub, selecting a template for a Rails app. Subsequently, the repository is connected in the Claude app by authorizing repository access rights in GitHub. Claude then generates simple “Hello World” code and creates a pull request that can be merged into the new repository.

  The video explicitly covers GitHub and the Claude app and is aimed at intermediate users.

• Multitasking With Agents: My 2026 Workflow
  29.4.2026, 12:01:10

  The video compares the AI platforms Claude and OpenClaw regarding their suitability for building business processes. Claude is described as trustworthy and mature, particularly for creative and strategic tasks. OpenClaw, on the other hand, is portrayed as immature but innovative, with shortcomings in setup, documentation, and reliability. Despite these weaknesses, OpenClaw has advanced the concept of agent hiring and could play a significant role long-term. The choice between platforms depends on priorities: trust and maturity (Claude) or innovation and potential (OpenClaw).

  The video explicitly covers Claude and OpenClaw and targets intermediate and advanced users who want to use AI tools for business purposes.

• VPS vs Mac Mini for OpenClaw
  28.4.2026, 14:00:18

  The video discusses the suitability of Claude Design for real-world workflows in product development. The author tests two main use cases: first, creating a new T-shirt marketplace, finding that while Claude Design generates appealing mockups, integration into an existing codebase and further development are problematic. Second, expanding an existing website with a design system analyzed from a GitHub repository. Here too, he sees difficulties in practical implementation. Instead, he prefers working directly in Claude Code with a self-created design system integrated into the codebase. The author identifies two meaningful use cases for Claude Design: as a visual planning tool in the early ideation phase for new products and for creating marketing assets like animations and presentations that match brand identity. He emphasizes that Claude Design is not suitable as a continuous tool from idea to finished product, but can be useful in specific phases and applications. He stresses that Claude Design is not appropriate as an end-to-end tool from concept to completion, but can be valuable in specific phases and use cases.

  The video explicitly covers Claude Design and Claude Code and is aimed at intermediate to advanced users who already have experience with AI-assisted product development.

• Build Your Next Startup Entirely From Your Phone
  25.4.2026, 14:01:07

  The video shows how to start a new project using a smartphone and the GitHub and Claude apps. First, a new repository is created in the GitHub app and a template for a Rails app is selected. Subsequently, the repository is connected in the Claude app to write code there. Claude then creates a simple “Hello World” webpage and creates a pull request that can be merged into the new repository.

  The video explicitly covers GitHub and Claude tools and is aimed at intermediate users.

• Can you trust OpenClaw with your business?
  25.4.2026, 14:01:34

  The video compares Claude and OpenClaw platforms regarding their suitability for building business processes. Claude is described as trustworthy and mature, particularly for creative and strategic tasks. OpenClaw is portrayed as immature but innovative, with shortcomings in setup, documentation, and reliability. Despite these weaknesses, OpenClaw has significantly advanced the concept of agent hiring. The thesis is that breakthroughs often come from new, unpolished platforms, not from established providers.

  Claude and OpenClaw are discussed; the video targets intermediate and advanced users.

• Where Claude Design actually fits
  24.4.2026, 12:00:29

  The video discusses the suitability of Claude Design for real-world workflows in product development. The author tests the tool across various use cases and arrives at mixed results.

  First, the use of Claude Design for creating a new T-shirt marketplace is demonstrated. A high-quality mockup is created that looks appealing but is difficult to integrate into existing workflows in practice. Export functions such as PDF, Canva, HTML, or handoff to Claude Code are rated as insufficient for professional product development. The lack of a planning and specification process necessary for successful implementation is particularly criticized.

  Another use case is extending an existing website with new pages or features while maintaining the existing design system. Here too, it becomes apparent that while Claude Design can analyze and create a design system from a GitHub repository, integration into the existing codebase is problematic. The author prefers instead to work directly in Claude Code with a self-created design system integrated into the codebase.

  The author sees genuine breakthroughs in using Claude Design as a visual planning tool in the early ideation phase and for creating marketing assets. For creating a metrics dashboard, it is shown how a mockup is created in Claude Design and subsequently used as the basis for detailed product planning in Claude. This particularly facilitates entry into product development for inexperienced users.

  Another practical application is creating animated videos and presentations that match brand design. Here, Claude Design offers specific templates for animations and slides that can be used directly.

  In summary, Claude Design is evaluated as useful for the early planning phase and creation of marketing assets, but not as a complete tool for product development from idea to finished product.

  Final note: The video explicitly covers Claude Design and Claude Code and targets intermediate users who already have experience with AI tools.

Melvynx (10 new videos)

• Codex : control your computer and your VPS with your iPhone
  19.5.2026, 16:00:15

  The video shows the integration of Codex, an OpenAI tool, with mobile devices, particularly iPhones, and its advantages over previous solutions like Cloud Remote Control. The user demonstrates how to connect their iPhone with the Codex app and gain remote access to various devices and services. This includes SSH connections to VPS (Virtual Private Servers), controlling a Mac, and continuing chats across different devices. Particularly highlighted is the ability to send commands to a VPS via iPhone and automate or control tasks. The user emphasizes the user-friendliness and efficiency of the integration, which allows working without complicated additional setup. The video also demonstrates accessing additional plugins via VPN that aren’t available in certain regions.

  The video explicitly covers OpenAI (Codex) and is aimed more at intermediate to advanced users who already have experience with remote access and VPS usage.

• Confession d'un Workaholic à SEOUL
  19.5.2026, 07:00:31

  The video showcases the YouTuber’s workspace and emphasizes the importance of an ergonomic setup for productivity. They recommend positioning the monitor at eye level to avoid physical discomfort, using a tripod for this purpose. Their setup consists of a single monitor, an Apple keyboard, and a Logitech mouse. The YouTuber works in a space rented through the Stitch Creator program and praises the benefits of this platform. They mention producing three videos in one day without leaving the room and highlight the efficiency of their workspace.

  The YouTuber doesn’t cover specific AI tools or models; the video is aimed more at intermediate or advanced viewers interested in productivity and workspace optimization.

• I MIGRATE Thumbfa.st to Convex + Tanstack Start ($1000 API Codex spent)
  18.5.2026, 16:01:13

  The YouTuber presents the migration of their Subfast application from the Next.js stack (Next.js, Prisma, PostgreSQL) to the TanStack stack (TanStack Start, Convex). They compare both stacks based on performance, user experience, and development processes. The new stack offers faster, synchronized UI and simplified code maintenance, as Convex centralizes all data and actions as a backend. The developer highlights Convex’s advantages, such as instant data synchronization and easy debugging through direct access to logs and debugging tools. The migration significantly reduced application complexity and increased development speed.

  The video explicitly covers Convex and TanStack Start tools and is suited for intermediate to advanced developers.

• Apple Maps vs Google Maps: The Americans’ choice
  17.5.2026, 07:00:38

  The video discusses Apple Maps compared to Google Maps, particularly within the Apple ecosystem context. The user emphasizes that Apple Maps combined with an Apple Watch provides practical navigation, as the watch gives haptic feedback for turns without needing to pull out the iPhone. However, it’s criticized that Apple Maps provides a less reliable interface than Google Maps, since Google Maps has more data and is already established in many regions. The video also highlights the high air quality in the region despite the USA’s general environmental issues.

  The video covers Apple Maps and Google Maps and is aimed at intermediate users already familiar with the Apple ecosystem.

• OpenAI doesn’t pay me
  17.5.2026, 06:16:42

  The video is about the challenge of adapting to new technologies, particularly in the context of AI tools. The speaker shares personal experiences switching from Claude to Codex after initially showing resistance to change. They describe how introducing AI has affected their YouTube views and how they initially felt frustrated. Ultimately, they emphasize the importance of adapting to new tools and making the best of them, without financial interests being involved.

  The speaker explicitly covers the AI models Claude and Codex and addresses an audience interested in AI tools, probably at an intermediate level.

• I'm abandoning Claude Code for Codex… let me introduce it to you
  16.5.2026, 16:00:40

  The video is a detailed review and demonstration of the Codex application after a week of intensive use. The user explains why they switched from Cloud Code to Codex, mainly due to cost efficiency and improved features. They show their Codex usage, including using work-trees for multitasking and integration with various tools like Z and Convex. The user highlights Codex’s advantages, such as the ability to use multiple agents simultaneously, a better interface, and the opportunity to use tokens more cost-effectively. They also demonstrate how they migrated their Skills and Agents from Cloud Code to Codex using symlinks. The user mentions preparing a masterclass on using Codex and invites viewers to use their Skills and resources.

  Final comment: The video explicitly covers Codex and is aimed at intermediate or advanced users.

• I respond to the angry ones
  16.5.2026, 10:35:16

  The video is a response to criticism from a user named Benjamin Code. The YouTuber defends themselves against accusations of being unqualified, disorganized, and dishonest. They acknowledge that their videos can sometimes be unstructured but emphasize that they’re pleased when their enthusiasm shows through. They also address specific complaints, such as the claim that you can’t exceed token limits with a maximal plan, explaining that they actually have. The YouTuber mentions their large presence on LinkedIn and YouTube to underline their experience and reach. They conclude by stating that they find such comments unnecessary and that they continue to view their videos as entertaining and not always serious.

  The YouTuber explicitly covers OpenAI and addresses both beginners and intermediate users.

• Better-Auth : the ultimate authentication tool with Convex (avoid Clerk)
  15.5.2026, 16:31:38

  The video discusses the pros and cons of Clerk, an authentication service, and compares it with Better Auth, an alternative solution. The author argues that while Clerk offers quick and easy integration, it can be problematic due to vendor lock-in and high costs. Better Auth is presented as a more flexible and cost-effective alternative offering greater control and customization options. The author shows how they implemented a comprehensive authentication solution with Better Auth including an admin dashboard and organization management, supported by AI agents. They emphasize Better Auth’s advantages, such as the ability to host and control everything yourself, as well as integration into their own stack, which they offer as part of their Nostac training.

  The video explicitly covers Clerk and Better Auth and targets intermediate to advanced users dealing with authentication solutions for their applications.

• I destroy NextJS
  15.5.2026, 09:16:47

  The video is a reflection by the creator on their criticism of Next.js and their general attitude toward technological change. They emphasize that they don’t fundamentally reject Next.js but rather have a direct and sometimes aggressive communication style that might create this impression. The core of their argument lies in emphasizing mental flexibility that allows embracing new tools and technologies. They argue that many developers hold onto outdated technologies out of habit or fear of effort, even though better alternatives might exist. With the introduction of AI tools like Claude, they now see the possibility of making migrations faster and more efficiently, significantly lowering the barrier to switching to new technologies. Their main thesis is that developers and people in general should be willing to question their tools and opinions and continue evolving.

  The creator covers Next.js and AI tools like Claude, with the video aimed more at intermediate and advanced developers familiar with technological migrations and decisions.

• NEW : The command that lasts longer than you 🍆
  20.5.2026, 16:00:23

  The video introduces the new “Slash Goal” feature in Codex and Cloud Code, which allows an agent to not interrupt a task until it’s completed. The user can define a goal that the agent then verifies and ensures is achieved. For example, you can instruct the agent to make all tests green or fix all TypeScript and ESLint errors without cheating or disabling rules. The agent then works on it until the goal is reached and automatically verifies this. The feature is particularly useful for tasks that are easily verifiable, such as optimizing tests or refactoring code. The user can track the agent’s progress and manually intervene if needed. The video also shows how to use “Slash Goal” in various scenarios and what advantages it offers over conventional methods.

  The video explicitly covers Codex and Cloud Code and is aimed at intermediate to advanced users.

Dave Ebbelaar (4 new videos)

• The Complete Guide to Hybrid Search in RAG (BM25 + Embeddings + Reranker)
  14.5.2026, 17:52:50

  This video is a detailed tutorial showing how to build a hybrid retrieval system from scratch that combines BM25, dense embeddings, reciprocal rank fusion (RRF), and a reranker. The focus is on creating a production-ready system that will be relevant in 2026. The tutorial begins by explaining the dataset used, the Financial QA dataset, which is part of the BEIR benchmarks. This dataset contains financial questions and associated answers used for evaluating the retrieval system.

  The tutorial walks through the process of creating BM25 and dense embedding indices, executing queries, and combining results with RRF. Then a reranker is added to further improve the results. The tutorial emphasizes the importance of evaluation and demonstrates how to measure system performance using normalized discounted cumulative gain (NDCG).

  At the end, it explains how to apply the system to your own projects, including creating your own evaluation dataset. The tutorial is designed for developers and engineers who already have basic knowledge of retrieval systems and want to use them professionally.

  Final note: The video covers OpenAI (for embedding models) and Cohere (for the reranker) and is geared toward intermediate to advanced users.

• Building Agentic RAG From Scratch in Pure Python
  10.5.2026, 09:57:56

  This video demonstrates how to build an agentic RAG (Retrieval-Augmented Generation) system from scratch in pure Python. The focus is on making enterprise data or private information accessible to large language models to enable their use in AI automation. The author, Dave Abalar, explains the differences between classical semantic RAG and agentic RAG, with the latter excelling through a feedback loop and repeated use of the language model’s intelligence.

  The system is built in several steps: First, simple tools are defined that can list, search, and read files. These tools work with Markdown files in the file system. The author shows how to implement these tools in Python, including using regular expressions to search for patterns in files. Next, a simple agent is created with these tools that can answer questions about the contents of Markdown files. The agent uses the tools in a loop to find the right information and correct itself.

  The author also covers production best practices, such as using Rust-based tools like ripgrep for faster and safer file searching, and implementing error messages that can be interpreted by the language model to improve the agent. He shows how to deploy the system in various environments like VPS, container apps, or serverless functions.

  At the end of the video, a complete example of an agentic RAG system in Python is presented that follows production best practices and can be deployed in real-world projects.

  The video covers OpenAI and is suitable for intermediate to advanced users.

• If I Started AI Freelancing in 2026, I’d Do This
  4.5.2026, 15:15:23

  **Summary:**

  The video content describes a three-stage framework that the author calls the “Data Freelancer Blueprint” for succeeding as a freelancer in AI and data. The three stages are:

  1. **Get Going:**
  – Overcome psychological barriers and start with simple but useful projects, often considered “boring,” like data automation or reporting.
  – Create three end-to-end projects you can demonstrate, and learn how to integrate code into real systems and deploy it.
  – Update your LinkedIn profile to clearly communicate what problems you can solve.

  2. **Getting Paid:**
  – Determine your hourly rate through research.
  – Use your network for warm introductions and conversations with decision-makers.
  – After the conversation, create a detailed project proposal with milestones, deliverables, and a cost estimate.

  3. **Get Good:**
  – Focus on improving leads, sales, and delivery.
  – Build long-term contracts to secure stable income.
  – Use various channels like LinkedIn, YouTube, and freelance platforms to generate leads.

  The author emphasizes that freelancing in tech is a safe and lucrative way to start a business and encourages viewers to take the first step.

  **Final note:**
  The video covers tools like N8N and Airtable (low-code/no-code solutions) as well as Python and TypeScript (custom code solutions) and is aimed at intermediate and advanced freelancers looking to enter or expand their business in the AI and data space.

• Programming Has Changed – Here’s What I Focus On Now
  23.4.2026, 18:05:51

  This video discusses the future of tech jobs and the relevance of current skills in a rapidly evolving landscape, particularly in the context of artificial intelligence (AI). The speaker emphasizes that software engineers, AI engineers, and data scientists will continue to be needed, but the requirements and ways of working will change. He introduces three concepts that describe how AI is being used in businesses: AI-enabled, AI-first, and AI-native.

  1. **AI-enabled**: Companies use AI tools to boost employee efficiency without fundamentally establishing new processes.
  2. **AI-first**: Companies optimize their processes and systems around AI, with AI agents playing a central role.
  3. **AI-native**: Companies are built from the ground up with AI agents, with minimal human intervention.

  The speaker advises focusing on the ability to help companies move from AI-enabled to AI-first and eventually to AI-native. This requires broad knowledge of the entire technology stack (full-stack skills) and the ability to analyze and automate business processes. He stresses the importance of not only possessing technical skills but also being able to identify and optimize business processes suitable for automation.

  The speaker sees the future of tech jobs in the ability to develop end-to-end AI automations and help companies transition to AI-driven processes. He recommends positioning yourself as a freelancer or consultant to help small and large businesses implement AI solutions.

  Final note: The video covers general AI developments and is geared toward intermediate and advanced tech professionals.

Niklas Steenfatt (1 new video)

• OpenClaw for Dummies
  26.4.2026, 18:21:37

  The video demonstrates step-by-step how to set up your own OpenCore AI assistant, starting with installation on a Hostinger server through connecting various tools to setting up email and Google services. The creator recommends treating the assistant like a new employee and granting it only the necessary access to minimize security risks. Tools like Tavily for internet research, Notion for databases, and Deepgram for voice message integration are presented. The video also explains how to set up recurring tasks and subagents as well as how to keep track of costs. For advanced users, there are tips on troubleshooting and using the command line.

  The video explicitly covers OpenCore, Hostinger, Anthropic, Tavily, Notion, Deepgram, Google Cloud, Excalidraw, and ChatGPT and is more suitable for intermediate to advanced users.

Fireship (7 new videos)

• I can’t believe this trial is real…
  15.5.2026, 18:51:21

  The video offers a humorous look at futuristic technologies from 2026, including an AI-powered smart toilet, intelligent hair-cutting machines, and an AI pocket pet. However, the focus is on OpenClaw, a personal AI assistant system that has been making waves since its release in January 2026. The creator demonstrates how to host and configure OpenClaw on a Hostinger virtual private server to solve specific problems, such as answering family inquiries in your own voice. The process includes setting up a Telegram bot, integrating 11 Labs for voice generation, and configuring tools to generate automated responses.

  The video explicitly features OpenClaw and Hostinger and is aimed at intermediate users, as it includes technical steps for setting up and configuring an AI assistant system.

• A single PR just hijacked the NPM registry…
  14.5.2026, 17:39:11

  The video introduces Claude Design, a new AI-powered platform from Anthropic based on the Opus 4.7 model that converts Figma designs into interactive prototypes, pitch decks, and production-ready UIs. The AI can process high-resolution images and offers advanced features like interactive animations, design variations, and even video editing. The video demonstrates creating an iOS onboarding flow for a fictional app called “Horse Tinder,” where the AI provides a good starting point but doesn’t always apply the design system correctly. Despite some limitations, Claude Design shows promising capabilities that could revolutionize traditional design tools and processes.

  The video explicitly features Anthropic’s Claude Design and Opus 4.7 as well as Google Cloud Run and is aimed at intermediate and advanced users.

• Every operating system concept in one video…
  7.5.2026, 17:32:34

  The video explains in detail how an operating system works from the moment the power button is pressed until shutdown. It begins with the bootloader that loads the operating system, then moves on to privilege rings that separate kernel and application rights. Virtual memory is described as a system that allows multiple applications to run in parallel without interfering with each other. The kernel builds the file system, loads device drivers, and enables interrupts that allow the system to respond to inputs. The kernel then starts the first process (PID1), which is the ancestor of all other processes. System calls allow applications to communicate with the kernel, and the scheduler manages CPU time for the many processes. Threads allow applications to perform multiple tasks simultaneously, and inter-process communication (IPC) allows different processes to communicate safely. Finally, the shutdown process is described, where all processes are terminated and the system shuts down safely.

  The video generally covers operating systems and their components without mentioning specific tools or vendors and is aimed at intermediate or advanced viewers.

• 732 bytes of Python just borked every Linux machine on earth…
  4.5.2026, 18:40:40

  The video addresses a critical security vulnerability in the Linux kernel called “copy fail” (CVE-2023-31431), which has existed since 2017 and was discovered by an AI tool. The vulnerability allows a local user to gain root access by writing four bytes to the page cache of a read-only file. All Linux distributions updated after 2017 are affected. The vulnerability was exploited through a Python script using the ONC ESN protocol and the AF_AGL interface. Although the vulnerability is not remotely exploitable, systems are strongly recommended to be updated. The video also mentions the role of AI in discovering security vulnerabilities and promotes Code Rabbit, an AI tool for improving code quality.

  The video explicitly features AI tools like the AI agent tool used by Theori and Code Rabbit, and is intended for intermediate to advanced users.

• GitHub is having some major issues right now…
  30.4.2026, 16:37:31

  The video “It’s 10 p.m. Do you know where your children are?” from The Code Report discusses the current problems and challenges facing GitHub, the leading platform for software development. It notes that GitHub has recently experienced massive reliability issues, including frequent outages, missing pull requests, and search functions that no longer work. The video creator attributes this to increasing strain from AI agents using the platform as a free resource. The example cited is Mitchell Hashimoto, creator of tools like Vagrant and Terraform, who is moving his open-source projects away from GitHub after struggling with outages for months. The video also mentions alternatives like GitLab, Codeberg, and Source Hut as potential fallback options. In conclusion, it emphasizes that despite GitHub’s problems, developers still have many options for hosting their projects.

  The video features GitHub and Microsoft and is aimed at intermediate and advanced developers.

• I finally found a use case for OpenClaw…
  23.4.2026, 18:26:39

  The video presents a humorous and satirical summary of technologies in 2026, including an AI-powered smart toilet, intelligent hair-cutting machines, and an AI pocket pet. The focus is on OpenClaw, a personal AI assistant system released in January 2026 that has since received numerous security updates. The creator attempts to use OpenClaw to automate requests from relatives who think he’s a JavaScript expert because of his YouTube videos. To do this, he hosts OpenClaw on a Hostinger virtual private server, configures a Telegram bot, and integrates voice output via 11 Labs to generate responses in his own voice. The video ends with a successful demonstration of automation that provides him emotional distance from his family.

  The video explicitly features OpenClaw, Hostinger, and 11 Labs and is aimed at intermediate and advanced users.

• Claude just got another superpower…
  21.4.2026, 17:35:43

  **Summary:**

  Anthropic has introduced Claude Design, an AI-powered platform that converts Figma designs into interactive prototypes, pitch decks, and production-ready UIs. The tool uses the new Opus 4.7 model, which offers higher image resolution (3.75 megapixels) and improved creativity. Claude Design can create interactive UIs with animations, variations, and even shaders, setting it apart from competing products like Google Stitch. In a practical demonstration, an attempt was made to create an iOS onboarding flow for a fictional app, where the AI provided a good starting point but had issues with design system consistency and image quality. Despite some weaknesses, Claude Design shows promising capabilities for the UI/UX design industry.

  **Final Comment:**
  The video features Anthropic’s Claude Design and Opus 4.7 as well as Google Stitch and Google Cloud Run, and is aimed at intermediate users.

Julian Ivanov | AI Automation (9 new videos)

• Use Claude Code 24/7 from anywhere #claudecode #claude #claudeai
  16.5.2026, 13:23:32

  The video shows how to use the Cloud Code app on your phone to manage projects like building and hosting a website without needing your computer to be on. Users give commands via voice input, and the cloud executes them—for example, changing a website’s color palette. The video demonstrates the simple interaction and shows how to configure the cloud to complete tasks independently without user intervention. At the end, the finished, live-hosted website is displayed in the browser.

  The video explicitly covers the Cloud Code app and is better suited for intermediate users.

• Let Claude Code work for you from your phone (Remote Control)
  16.5.2026, 13:23:09

  The video shows how to install Claude Code from Anthropic on a server and control it via the Remote Control function using your phone to work on projects from anywhere. The user demonstrates creating a website, deploying it on a server, and making adjustments from a phone without needing to sit at a PC. Various commands like `Remote Control`, `Set a Goal`, and `Loop` are explained, allowing you to give Claude Code tasks that execute automatically until a specific goal is reached or at regular intervals. The user uses a Hostinger server with Claude Code pre-installed and shows how to set up DNS entries for a domain to make the created website live. Finally, two useful commands are introduced: `Slash Goal`, to instruct Claude Code to complete a task until a certain condition is met, and `Slash Loop`, to have Claude Code perform a specific action at regular intervals.

  The video explicitly covers Claude (Claude Code) and is intended for intermediate users.

• I hired Claude Code as my video editor
  11.5.2026, 17:02:17

  The video shows how to edit videos using AI tools like Claude Code, Hyperframes, and Claude Design without using traditional editing software. The process involves three main tools: Videowise, Hyperframes, and Claude Design. Videowise cuts the video based on the transcript created via 11 Labs. Hyperframes generates animations and motion graphics based on HTML, CSS, and JavaScript. Claude Design enables creating animations and designs in the browser without coding and integrates branding. The workflow is explained step by step, including tool setup and usage. It demonstrates how to cut a video, add animations, and render the final result in 4K. The video is suitable for intermediate users who want to use AI tools like Claude Code, Hyperframes, and Claude Design.

• These 20 Claude Code tricks save you hours
  7.5.2026, 19:15:23

  The video presents 20 tricks and best practices for effectively using Claude Code in various work situations. The key tips include:

  1. **Use Plan Mode**: Create a plan before starting a project or making major changes and discuss it with Claude to avoid misunderstandings.
  2. **Ask Questions**: Have Claude ask clarifying questions before starting work to ensure all details are clarified.
  3. **Discuss, don’t command**: Treat Claude as a sparring partner and openly present problems instead of prescribing solutions.
  4. **Autoaccept Mode and Permissions File**: Use Autoaccept Mode for more efficient work and create a Permissions file to restrict access to sensitive files.
  5. **Use Voice Input**: Enter long prompts via voice input to save time and convey context better.
  6. **Slash init for Project Onboarding**: Use the Slash init command to quickly onboard Claude to a project and create project memory.
  7. **Maintain Cloud MDI**: Actively maintain the Cloud MDI file and store important information there to give Claude relevant info in every session.
  8. **Emergency Stop and Rewind**: Use the Escape key to stop or reset Claude if something goes wrong.
  9. **File Mentions as Shortcuts**: Reference files directly in the chat to give Claude easy access to important information.
  10. **Use Screenshots**: Use images or screenshots to better explain designs or layouts.
  11. **Self-Check**: Instruct Claude to review its own work to avoid correction loops.
  12. **One Task per Session**: Work on only one task per chat to avoid overwhelming the context window.
  13. **Use /context**: Check the context status to see what occupies the context window and free up space.
  14. **Slash Compact and Slash Clear**: Summarize the context window with Slash Compact or clear it with Slash Clear to free space.
  15. **Custom Skills**: Outsource regular tasks to Skills to avoid having to re-explain them to Claude each time.
  16. **Use Models by Task**: Use different models (HighQ, Sonnet, Opus) depending on task complexity.
  17. **Hooks for Notifications**: Use hooks to be notified when Claude has completed a task.
  18. **Subagents and Agent Teams**: Use Subagents for token-intensive tasks and Agent Teams for complex, parallel work.
  19. **Ultraathink Keyword**: When facing difficult problems, use the keyword “Ultraathink” to give Claude more time to think.
  20. **Use Worktrees**: Use Worktrees for parallel work on different features of a project to avoid conflicts.

  The video explicitly covers Claude (Claude Code) and is intended for intermediate users.

• Claude Code has never been easier!
  3.5.2026, 15:26:48

  The video presents the latest updates to Anthropic’s Claude Code Desktop App, which has significantly improved the use of Claude Code. Claude Code is a tool that runs on your own computer and has access to a folder to create, read, and execute files. Previously, Claude Code could only be used in a limited way in the desktop app, but the update now enables much more comprehensive use. Users can now work directly with Claude Code in the desktop app, view files, edit them, and even preview created apps in testing. The video shows how to create a flashcard app by granting Claude Code access to a folder and then describing the app. Claude Code plans and creates the app automatically, and users can accept or adjust the plan. The desktop app now also has an Auto Mode where Claude Code executes commands that aren’t dangerous and only asks for permission on more risky commands. Additionally, users can view created files, edit them, and even open the terminal to run further commands. The video also shows how to run multiple sessions simultaneously and what limitations still exist, such as displaying images and PDF files. Overall, the desktop app now offers much better overview and functionality for using Claude Code.

  The video explicitly covers Anthropic’s Claude Code and is intended for intermediate users.

• Look into the future with this AI swarm intelligence (MiroFish)
  26.4.2026, 14:04:17

  The video introduces **MiroFish**, an open-source project for simulating social dynamics with AI agents. The 20-year-old developer from China created a platform within 10 days that enables the creation of virtual people with their own personalities, opinions, and behaviors that interact in a simulated world. MiroFish uses uploaded context data (e.g., market research reports, product information) and simulates responses to events like price increases or product launches. The simulation runs in five phases: creating a knowledge graph, generating virtual personas, simulating social media interactions, analyzing results, and deep interaction with agents. The video demonstrates MiroFish’s application using a fictional app called “Mealmate” that automates meal planning for families. The simulation shows how different target groups react to the product, including price acceptance and potential improvements. The creator also explains how to install and configure MiroFish locally or on a virtual server, including using OpenAI models and the Z-Cloud database.

  **AI Tools/Models/Providers:** OpenAI (GPT-4, GPT-4.1 Mini), Z-Cloud, Claude Code, Hostinger, Open Source (MiroFish) – better for intermediate users.

• Simulate the future with AI #aiagents #ki #ai
  26.4.2026, 14:05:04

  The video introduces the open-source project **MiroFish**, which creates a simulated world with hundreds of AI agents that interact with each other. Each agent has their own personality, opinion, and biography. Users upload context material, ask a question (e.g., about reactions to a price increase or new advertising campaign), and MiroFish generates virtual people and organizations discussing that question. At the end, you receive a detailed report and can communicate directly with each agent. The video shows a demo with a SaaS product idea and explains how to set up MiroFish yourself in 2 minutes.

  The video covers the open-source tool **MiroFish** and is better suited for **intermediate** users.

• Hermes Agent: The new self-improving OpenClaw
  21.4.2026, 13:07:46

  The video introduces Hermes, a new AI agent positioned as a competitor to OpenClaw. Hermes was developed by News Research, an AI research lab from New York, and is open source. The main difference from OpenClaw lies in Hermes’ “Self Improvement Loop,” an integrated learning cycle that allows the agent to continuously improve. This process includes creating and updating Skills, saving relevant information in Memory files, and analyzing past conversations to build a more comprehensive user profile. The video also shows how Hermes is installed and configured, both locally and on a server, and compares the features and benefits of both agents. It’s recommended to try Hermes, especially for users looking for an AI that learns and improves independently.

  **Final Comment:** The video explicitly covers Hermes and OpenClaw and is better suited for intermediate users familiar with AI agents and their installation and configuration.

• Use Claude Code for free: Code unlimited without a powerful PC
  20.5.2026, 13:41:18

  The video shows how to use Claude Code for free by connecting it to free language models from Open Router. Claude Code is a kind of “harness” that connects various AI models with tools and files, and typically runs with paid models like Sonnet, Opus, or High from Anthropic. By connecting to Open Router, you can access free models like GPT OSS, Minimax M2.5, or Deepseek V4 Flash. The setup requires creating an API key at Open Router and configuring a Settings.json file in Claude Code. Users can then choose between different free models and use Claude Code at no cost, as long as no sensitive data is processed. Importantly, free models from Open Router have strict rate limits, which can be increased by crediting $10 to your Open Router account without actually incurring costs.

  The video explicitly covers Claude, Open Router, and specific models like GPT OSS, Minimax M2.5, and Deepseek V4 Flash and is better suited for intermediate users.

Mark Kashef (7 new videos)

• How to Use /goal to Build a Self-Improving OS
  17.5.2026, 15:30:23

  The video introduces the new “/goal” function in Codecs and Cloud Code, which can be used beyond technical tasks for optimizing agentic operating systems (Agentic OS). The author demonstrates five practical use cases: “Clean” (cleaning up skills and rules), “Sharpen” (improving skills based on specified criteria), “Revive” (reviving abandoned projects), “Forge” (extracting recurring prompts into new skills), and “Maintain” (automated system maintenance). The video explains how the function works through a goal specification and a separate evaluation agent. The author demonstrates the application using concrete examples and emphasizes the ability to make your own work environment more efficient.

  The video explicitly addresses the /goal function in Cloud Code and is intended for intermediate or advanced users who are already familiar with agentic systems.

• Why 90% of Your Claude Skills Are Dead Weight
  13.5.2026, 20:00:29

  The video addresses challenges and best practices when using skills in Claude Code. The author criticizes that many users accumulate too many useless or even harmful skills that impair performance. He explains that skills consume tokens and can overload context windows, leading to inefficient and error-prone interactions. The author presents eight tips for optimizing skills:

  1. **Run it cold**: Test whether a vague prompt triggers the right skill.
  2. **Check the budget**: Ensure the description is precise, but not too long.
  3. **Ask user input tool**: Integrate a questionnaire to ensure the skill has all necessary information.
  4. **Copy-related rules**: Add rules for tonality and formatting if the skill works with text.
  5. **Rate the skill**: Have the user rate the skill and ask for improvements.
  6. **Wrong primitive**: Check whether the skill is the right tool for the task or whether it would be better implemented as a rule or CLI command.
  7. **Audit with Claude Code Guide Agent**: Use a predefined prompt to systematically audit and optimize skills.

  The author emphasizes the importance of progressive disclosure and good user experience to make skills efficient and user-friendly. He also shows how to consolidate and test skills to avoid redundancy and improve performance.

  **Final comment:** The video explicitly addresses Claude by Anthropic and is aimed at intermediate users who already have experience with skills in Claude Code.

• Build Your Agentic OS Better Than The 99%
  9.5.2026, 20:00:14

  The video covers practical implementation and optimization of agent-based operating systems (Agentic OS) like Open Claw, Hermes, or Claude Code to achieve real business value. The focus is on the often-neglected “grunt work” behind the scenes that’s necessary to effectively deploy such systems. The author emphasizes the importance of data readiness and organization before tackling dashboards or fancy features.

  Key points include the use of skills (both project-specific and global), hooks (event-based automations), and Claude MDs (as central control documents). The author introduces a tool called “Skill/Silver Platter” that helps organize and summarize data to improve agents’ analytical capabilities. Tactical tips are provided on how to effectively use integrations and APIs to optimize systems.

  The video presents three case studies (Marco, Sally, and Dr. Sana Anwar) illustrating how the described methods can be applied across different industries and business models. The author emphasizes the importance of strategically deploying agents and continuously improving them, similar to training and developing employees in a company.

  At the end, the “Skill/Silver Platter” tool is offered for download and a course is referenced for deeper exploration of the topic.

  The video explicitly addresses Claude Code and is suitable for intermediate to advanced users who already have some experience with agent-based systems.

• This Claude Code Setup Runs My Entire Business
  3.5.2026, 19:00:21

  The video presents a detailed demonstration of a custom-built AI Operating System (AIOS) that the creator uses for his business. The system consists of multiple agents, each covering specific tasks and expertise. At the core of the system is a “Hive Mind” that serves as a shared state of memory and visualizes agent activities and knowledge. The creator shows various views and features of the system, including a 3D and 2D graphics view, a task list, and a “War Room” function for interacting with agents via text and voice.

  A practical example is the use of a meta-agent connected to the Meta Command Line Interface to analyze ad performance and generate reports. The system also enables task automation and reminder creation. The creator emphasizes that the system is built on solid data organization and that implementation requires time and iteration. He offers resources and a carbon-copy version of his system, accessible via a link in the video description.

  Final comment: The video explicitly addresses Claude, OpenAI (Cloud Code), Gemini, and specific tools such as Telegram, Discord, Slack, Loom, and SQLite. It is intended for intermediate and advanced users.

• You Can Make Claude + Codex Plan Together. Here's How.
  28.4.2026, 19:00:35

  The video introduces a tool called “Claudeex” that automates collaboration between Claude Code and Codeex to create detailed and well-thought-out project plans. The process involves multiple rounds in which Claude Code creates a plan and Codeex reviews it, identifies errors, and suggests improvements. Claude Code incorporates these suggestions and the process repeats until a specified number of rounds is completed. The tool also offers features like “/review” for manual review, “/cancel” to abort the process, and “/rollback” to fully reset. A practical example demonstrates how Claudeex is used to create a detailed plan for building a specialized website that tracks user activities. The comparison between a plan created with only Claude Code and a plan created with Claudeex shows the improved detail depth and robustness of the latter.

  The video explicitly addresses Claude Code and Codeex and is intended for intermediate or advanced users who already have experience with these tools.

• You Can Run Claude AND Codex Together. Here's How.
  26.4.2026, 19:30:32

  The video shows how to combine the strengths of the AI models Claude Code and Codex to achieve better results. It introduces an OpenAI plugin that allows you to use Codex as a kind of “sidekick” for Claude Code. The author explains that each model has its own strengths and weaknesses, and that combining both models leads to better results. The plugin offers various commands, such as code review, adversarial review, and code rescue, which allow you to review and improve Claude Code’s code. The author demonstrates the use of the plugin in various scenarios, such as reviewing an existing codebase, planning new features, and reviewing code before shipping. He emphasizes that combining both models leads to more efficient and effective development.

  Final comment: The video explicitly addresses Claude Code, Codex, and OpenAI and is intended for intermediate to advanced users.

• Master ALL 7 Levels of Claude Code Memory
  22.4.2026, 18:30:28

  The video explains how to create a personalized memory system for Claude Code rather than using pre-built solutions. The speaker emphasizes that each memory system should be unique and tailored to the specific needs of the user. He walks through a three-stage process: cloning existing GitHub repositories, comparing and analyzing these repositories with Claude Code, and extracting relevant design patterns and code. Next, the video shows how to use this information to create a customized memory system aligned with your daily workflows. The speaker stresses the importance of continuously adapting and iterating the memory system, as requirements and workflows may change over time. Various building blocks for a good memory system are presented, such as identity, critical context, working memory, long-term and episodic memory, as well as mechanisms like decay and memory promotion. Additionally, a skill called “Memory Architect” is introduced that guides the user through an interview process to create the perfect architecture for their memory system. Finally, the video demonstrates how to integrate this memory system into your daily use of Claude Code, including through the use of hooks and automatic memory injection.

  The video explicitly addresses Claude Code and is suitable for intermediate users who already have basic knowledge of using Claude Code and are ready to take somewhat more technical steps to optimize their memory system.

Everlast AI (10 new videos)

• AI Researcher: Forget ChatGPT, THIS is the next breakthrough! World Models Explained (Daniel Cremers)
  19.5.2026, 15:15:29

  The video is an interview with Professor Dr. Daniel Cremers, a leading expert in artificial intelligence and computer vision. Cremers discusses AI development, particularly the breakthrough in image classification in 2015, which he believes was more important than the successes of AlphaGo and ChatGPT. He emphasizes the significance of world models, which enable spatial understanding of the world, and distinguishes them from multimodal language models. Cremers sees major applications for world models in areas such as autonomous driving, robotics, defense, and personalized medicine.

  He criticizes the current focus on national LLMs and foundation models, advocating instead for a diversity of approaches and the development of new methods. Cremers stresses the importance of energy efficiency in AI and the need to learn from humans to develop more energy-efficient algorithms. He sees the future in robotics and the integration of AI tools into everyday life to make people’s lives easier.

  The video explicitly covers AI tools and models from DeepMind (AlphaFold), Nvidia (GPUs), and Google (TPUs), as well as the importance of open-source and research initiatives. It is intended for intermediate and advanced viewers seeking a deeper understanding of AI development and its applications.

• AI News: THIS changes everything! New Model, Claude is BACK, Codex in ChatGPT & BCI Interview
  17.5.2026, 08:15:32

  The video covers several current developments and trends in artificial intelligence and humanoid robotics. Here are the main points:

  1. **AI Model Updates**:
  – **Claude**: Increased usage limits by 50% and introduction of a new agent view, enabling management of multiple agents in parallel.
  – **OpenAI**: Integration of Codex into the ChatGPT mobile app, allowing remote control of Codex on desktop and task completion from your phone.
  – **Thinking Machine Labs**: Introduction of a new model optimized for multimodal input (audio, text, image, video) and capable of making tool calls during conversation.

  2. **Humanoid Robots**:
  – **Figer**: Confirmation of design lock for the next generation of Figer F04 and live stream of a fully autonomous 8-hour shift of Figer 3.
  – **Unitree**: Introduction of a real-world drivable mecha and Unistore, an app store for humanoid robots.

  3. **AI in Enterprises**:
  – **Anthropic**: Overtakes OpenAI in business adoption and receives investment offers valuing the company at over 900 billion dollars.
  – **OpenAI**: Founding of OpenAI Deployment Company to support businesses in implementing AI technologies.
  – **Claude for Small Businesses**: Introduction of a collection of skills and MCP connectors for small businesses.

  4. **Research and Future of AI**:
  – **Professor Dr. Thorsten Zander**: Discusses challenges of AI models, particularly the lack of true world understanding and empathy. He introduces passive brain-computer interfaces (BCIs) as a potential solution.
  – **Google IO**: Expectations for the biggest Google event of the year, including the introduction of Gemini Spark, a 24/7 agent that autonomously completes tasks.

  5. **AI Business Ideas and Tools**:
  – **Browser Use and Kimy Web Bridge**: Tools enabling proactive agents in the browser and task automation.
  – **Make CLI**: Introduction of a command-line interface for the Make automation platform.
  – **Augustus**: A bank optimized for the AI era, designed for agent-initiated workflows.

  6. **Social Experiment**:
  – An experiment shows that even experts cannot always distinguish between AI-generated and genuine human works, underscoring the importance of quality seals.

  The video explicitly covers AI models and tools from Claude, OpenAI, Thinking Machine Labs, Browser Use, Kimy, Make, and Augustus. It is intended for intermediate and advanced users as it addresses in-depth technical and economic aspects of AI development.

• China Insider Reveals: There’s NO way back anymore! THIS is rolling toward us by 2030 (Jörg Wuttke)
  14.5.2026, 15:15:38

  The video offers deep insight into China’s current economic and political situation, particularly in the context of innovation, technology, and demographic challenges. Here are the key points:

  1. **Innovation and Overcapacity**: China has a deep pool of engineers and is leading in many areas such as AI, humanoid robotics, energy, and electric vehicles. However, China systematically produces overcapacity, leading to deflation and economic problems. This is because state-owned enterprises don’t disappear from the market even when they don’t make profits.

  2. **Demographic Challenges**: China is aging rapidly and has a low birth rate. The population is expected to decline to approximately 500 million by 2060. This leads to a labor shortage, which China wants to offset through the use of AI and robotics.

  3. **Technological Independence**: China seeks to become independent from Western technologies, particularly in semiconductors. This is a response to restrictive U.S. policy limiting exports of high-tech to China.

  4. **Export Pressure**: Due to overcapacity and weak domestic consumption, China depends on exports. This creates strong competitive pressure on global markets, particularly in Africa, South America, and Southeast Asia.

  5. **Political and Economic Strategies**: China relies on long-term plans, such as the 15-year plan, to achieve its goals. However, there are internal challenges, such as population aging and migration from rural to urban areas.

  6. **Corporate Strategies**: Chinese companies are more risk-taking and closer to customers than their Western competitors. This enables faster development and adaptation to market needs.

  7. **Geopolitical Implications**: Demographic and economic changes in China will significantly influence the global geopolitical landscape. Africa will gain importance as a supplier, while China loses influence.

  The video is suited for intermediate and advanced viewers as it addresses complex economic and political connections. No specific AI tools or models are discussed, but rather general trends and strategies.

• AI Experts React: THIS everyone is missing! Musk’s Claude deal, China’s robot pressure & EU kills AI Act
  12.5.2026, 15:15:26

  The video is a discussion about current developments and trends in artificial intelligence, technology, and the future. The participants are Professor Dr. Andreas Moring, Professor Dr. Pero Mitic, and Kim Isenberg, who discuss various aspects of AI usage, robotics, automation, and their impacts on society and economy.

  **Main Topics and Points:**

  1. **AI Models and Infrastructure:**
  – **Anthropic and Elon Musk:** Anthropic now uses Elon Musk’s data centers (Colossus 1 and 2) for its AI models. This is seen as a strategic move, as Musk needs to rent out computing power to avoid leaving it unused.
  – **Gemini and Apple:** Apple relies on Google Gemini for Siri after negotiations with Anthropic failed. This shows that Apple doesn’t necessarily need the best AI model, but one that’s good enough for the mass market.
  – **Humanoid Robots:** Boston Dynamics shows progress in robotics, particularly with the Atlas robot capable of executing complex movements. This underscores the importance of robotics in production, logistics, and service.

  2. **Economic and Political Aspects:**
  – **China vs. Europe/USA:** China is far ahead in many areas of technology and infrastructure, particularly in robotics and AI. Europe, on the other hand, faces difficulties keeping up, both due to political decisions and economic challenges.
  – **Job Losses from AI:** Companies like Coinbase, PayPal, and Cloudflare are laying off employees and attribute this to AI adoption. The discussion centers on whether these are truly AI-driven layoffs or if economic difficulties are the real reason.
  – **Regulation and Data Protection:** The EU is discussing stricter regulations, such as banning VPNs for child protection. This is viewed critically as a restriction of freedom.

  3. **Healthcare and AI:**
  – **AI in Healthcare:** Google presents studies showing that AI diagnoses are often better than those of physicians. This could revolutionize the healthcare sector but also raises questions about self-perception and technology dependency.

  4. **Education and Future Readiness:**
  – **Education Systems:** It is emphasized that schools and universities must change to foster judgment and critical thinking rather than just conveying information.
  – **AI Investments:** Companies should invest in AI to remain competitive. This includes developing AI-powered applications and using platforms like Cloud Code.

  **Concluding Remarks:**
  The video explicitly covers models and providers such as Claude, OpenAI, Gemini, and open-source solutions. It is intended for an advanced audience already familiar with AI and technology seeking deeper insights.

• AI News: Claude improves while SLEEPING! Musk saves Anthropic, Codex & GPT Realtime Updates
  10.5.2026, 08:15:10

  The video covers several current developments and updates in artificial intelligence and agentic coding. Here are the key points:

  1. **Elon Musk’s SpaceX Deal with Anthropic**: The deal doubles the 5-hour usage limit in Cloud Code, while weekly limits remain unchanged. This is part of a partnership where Anthropic runs cloud models on SpaceX’s Colossus-1 supercomputer.

  2. **Gemma 4**: Google’s open-source model is now three times faster through multitoken prediction (MTP drafter). It can be used in Cloud Code, though with performance limitations.

  3. **Cloud Managed Agents**: Updates include multi-turn sessions, webhook integration, and the new “Dreaming” function, which addresses the memory problem of agents. This function was discussed with Vincent Pistor from Cogni, a startup specializing in agent memory.

  4. **Gemini Updates**: Google Gemini receives new features such as skills and scheduled actions. Additionally, Gemini 3.1 Flashlight was made publicly available, a cost-effective model for high-volume tasks.

  5. **Codex Cloud vs. Cloud Code**: Codex Cloud has dramatically caught up in downloads and offers new features such as a Chrome extension for browser automation.

  6. **Comparison of Remotion and Hyper Frames**: Both tools enable creation of videos and animations via text prompt. Hyper Frames offers faster onboarding and more reliable results, while Remotion is better suited for scaling.

  7. **OpenAI’s Realtime 2 Model**: This model is designed for agentic tasks and enables better integration into software and user interfaces. It is the engine behind ChatGPT’s Advanced Voice Mode.

  8. **AI Business Idea of the Week**: The App Store shows a dramatic increase in apps, attributed to the growing importance of agentic coding. Companies like Mercedes use agents to streamline their IT infrastructure.

  The video explicitly covers OpenAI, Gemini, Cloud Managed Agents, Codex, Remotion, Hyper Frames, and specific tools like Cogni. It is intended for intermediate and advanced users who want to stay up to date with the latest developments in the AI world.

• “You’ll be in for a rude awakening” Robotics Professor on China, Humanoids & the Future
  7.5.2026, 15:15:00

  The video is an interview with Alexander from Everlast AI about the current state and future of humanoid robotics, with a focus on the robot assistant Gami from TU Munich. Main topics include exponential development of robotics, integration of Visual Language Action Models (VLAs), challenges in manipulation and sensitivity of robots, and ethical and legal questions regarding liability of AI systems. Alexander emphasizes the importance of design and interaction design for robot acceptance in society and discusses the role of open source and proprietary solutions in robotics. He sees major advances in simulation and collective robot learning but warns of challenges in safety assurance and liability. The video explicitly covers models and providers such as Nvidia (Omniverse, Kosmos) and emphasizes the importance of fundamental research and industrial application. It is intended for intermediate and advanced viewers as it contains in-depth technical and ethical discussions.

  Concluding Comment: The video explicitly covers Nvidia (Omniverse, Kosmos) and is intended for intermediate and advanced viewers.

• Robotics Expert: Forget Humanoid Robots! THIS will actually happen (Dr. Hendrik Susemihl)
  6.5.2026, 15:15:00

  The video is an interview with Dr. Hendrik Susemihl, founder of Goodbites, a company developing fully autonomous robot kitchens. Goodbites produces over 50,000 meals daily and won the Robotics Award 2026 at Hannover Messe. The company supplies autonomous robot kitchens to the U.S. Army and is the global leader in this field.

  Hendrik Susemihl discusses the importance of Physical AI—AI with a physical body—and how it will fundamentally change our daily lives. He explains why cooking is more difficult to automate than factory work and how Goodbites won the U.S. Army as a customer. He also addresses Germany’s role in the global robotics race and emphasizes the necessity to think boldly and act quickly to keep up with competition from the USA and China.

  Susemihl highlights that while Germany is technologically leading, it lacks the ability to build global companies. He stresses the importance of speed and a willingness to experiment as well as the need to think boldly to keep up in competition. He sees the biggest mistakes of German companies in being too passive and not experimenting enough.

  In summary, the video discusses the importance of Physical AI and Germany’s role in the global robotics race. It emphasizes the necessity to think boldly and act quickly to remain competitive.

  The video discusses specific tools and providers such as Goodbites and is intended for intermediate and advanced audiences.

• Don’t Use Codex UNTIL you watch this video! (The ChatGPT SuperApp)
  5.5.2026, 15:15:00

  The video presents 34 tips and tricks for using Codex, a new SuperApp by OpenAI meant to replace ChatGPT. Here are the key points:

  1. **Basics**: Codex can be used like ChatGPT but offers additional features such as direct access to local folders and files.
  2. **How It Works**: Codex can access local folders directly and edit files, which is a major advantage over ChatGPT.
  3. **Excel Spreadsheets**: Codex can directly create and edit Excel spreadsheets in local folders.
  4. **Design Customization**: The Codex interface can be customized to individual needs, including font size, color scheme, and typeface.
  5. **Skills and Plugins**: Codex offers various skills and plugins that extend functionality, such as creating Word documents and PDFs.
  6. **Subagents**: Codex can use multiple subagents simultaneously to handle complex tasks and manage context.
  7. **Browser and Computer Use**: Codex can control the browser and local applications, facilitating task automation.
  8. **Automations**: Codex can set up automations to handle recurring tasks.
  9. **Chronicle Research Preview**: A feature that builds memories and context based on daily workflows.
  10. **Open Source**: Codex is open source, allowing users to add additional features.

  The video is intended for intermediate users and explicitly covers Codex, OpenAI, and specific tools such as Remotion and Paper.

• AI News: Codex “Goal” works for DAYS, Claude takes over ADS, Opus 4.7 hacked & OpenAI “Goblins”
  3.5.2026, 08:15:00

  The video covers various current developments and trends in AI technology. It begins with the introduction of Project Deal by Elanropic, which enables trading between AI models and is said to have brought eBay to a standstill. It also introduces the new Codex Goal function, which allows AI agents to work autonomously for several days. New features from Gemini and Cloud Code, directly integrated into CAD software, are also mentioned. The token problem with Cloud Code is addressed as officially confirmed, while OpenAI massively subsidizes Codex.

  Another focus is on AI system security. Johann Rehberger, a well-known AI security researcher, demonstrates how to manipulate the memory of Cloud Opus 4.7 with a ChatGPT image. He also discusses security vulnerabilities in Cloud Cowork and other attack vectors.

  The video also introduces the new Meta CLI, which enables complete control and management of advertisements through AI agents. It shows how to use this tool to analyze campaigns and create new creatives.

  Additionally, updates in Microsoft 365 and open-source alternatives to American AI tools such as MicS for the legal sector are presented. The video ends with a discussion about AI job losses and AGI’s impact on the job market, based on statements from Demis Hasabis and a discussion with Professor Peromitsicit and Professor Dr. Andreas Moring.

  **Concluding Comment:** The video covers OpenAI, Cloud Code, Gemini, Codex, and specific tools like Meta CLI and is suited for intermediate and advanced users.

• The End of Work: Why 80% will lose their jobs & what comes next (Post-Labor Economy)
  30.4.2026, 15:15:00

  The video is a discussion about the impacts of AI and automation on the world of work and society. The participants are Professor Dr. Pero Mitic, Professor Dr. Andreas Moring, and Kim Isenberg, moderated by Leo.

  The discussion begins with the thesis that AI and robotics will massively replace jobs in the coming years, potentially leading to a post-labor society. It is argued that this affects not only entry-level positions but also highly qualified professions such as lawyers and physicians. The participants discuss various scenarios, including a nightmare scenario with social unrest and a permanent underclass, a crisis scenario with transition difficulties, and an abundance scenario in which AI and robotics lead to a life of plenty.

  Various solution approaches are discussed, including universal basic income (UBI), universal basic services, robot taxes, and promotion of worker ownership. The participants agree that wealth redistribution is necessary to prevent social unrest. They also discuss AI’s role in science and the possibility that AI could generate new scientific insights.

  The discussion concludes with the question of how to move the topic out of the AI bubble and into broader society. It is suggested that each individual should take the first step and discuss the topic in their own circles.

  **AI Tools/Models/Providers:** Claude, OpenAI, Gemini, Open Source, specific tools such as Cursor, Lovable, Cline, n8n, etc.
  **Target Audience:** Intermediate to Advanced.

No Priors: AI, Machine Learning, Tech, & Startups (7 new videos)

• Pax Silica: Inside the Trump Administration’s Tech Strategy with Jacob Helberg
  14.5.2026, 10:01:32

  The video is an interview with Jacob Helberg, Under Secretary of State for Economic Affairs, about the “Pax Silica” initiative. This initiative is an economic security coalition aimed at securing AI supply chains for the US and its allies. Helberg explains that Pax Silica pursues an ecosystem-based approach and already includes 14 countries. A central project is establishing a “forward-deployed industrial base” in the Philippines, where 4,000 hectares of land will be used for industrial development. This zone is intended to offer a combination of American legal systems and Philippine industrial advantages.

  Helberg emphasizes the importance of collaboration with the private sector, as the US does not want to rely on state-operated supply chains. Instead, the initiative aims to create commercially viable platforms that can also function independently of the state. The initiative seeks to reduce dependence on China and diversify supply chains, particularly in areas like robotics and rare earth elements.

  The video also addresses the differences between the American strategy and China’s Belt and Road Initiative, with Helberg highlighting the advantages of the American approach, which relies on partnerships with the private sector and ethical business practices. He emphasizes the importance of innovation and the role of private capital in solving supply chain problems.

  The video is better suited for Intermediate and Advanced audiences and does not focus on specific AI tools or models, but rather on political and economic strategies.

• Amex Global Business Travel: The World’s First AI Take Private with Long Lake CEO Alexander Taubman
  11.5.2026, 10:01:04

  **Summary:**

  Long Lake Management, a company specializing in acquiring and transforming businesses through AI, recently announced its intention to acquire American Express Global Business Travel (AmEx GBT) for $6.3 billion. This would be the first AI-driven acquisition of a publicly traded company. Long Lake has already acquired 30 companies and transformed them with its Nexus AI platform. This platform automates workflows, improves employee productivity, and drives company growth.

  Alex Topman, CEO of Long Lake, explains that the Nexus platform shares approximately 80% of infrastructure across various industries and can be deployed within days of an acquisition. This leads to immediate margin increases and growth. Long Lake focuses not on cost reduction but on growth and customer experience. Through AI-driven automation, employees can serve more customers, leading to higher organic growth rates.

  Topman emphasizes that Long Lake doesn’t just sell software but acquires companies to build deeper business relationships and achieve better results. This enables closer collaboration between employees and engineers, leading to better solutions and faster innovation. Long Lake aims to be the best employer in every industry it operates in, thereby attracting talented employees.

  The acquisition of AmEx GBT exemplifies Long Lake’s long-term strategy of acquiring companies and holding them for the long term rather than selling them short-term. Topman views AI as a positive-sum game that benefits both employees and customers.

  **Closing Comment:**
  The video covers Long Lake Management and their Nexus AI platform, which is used to transform businesses. It is better suited for Intermediate and Advanced audiences, as it focuses on complex business strategies and AI applications.

• Cheaper AI Does the Opposite of What You’d Expect
  6.5.2026, 13:06:28

  The video discusses the impact of cost reductions on AI demand and efficiency. The main idea is that lowering AI model costs increases demand, as both consumers and developers integrate more intelligence into their applications. Consumers seek the best answers and experiences, while developers incorporate more intelligence with cheaper AI models. This leads to longer and more complex AI agents that provide better user experiences. Ultimately, this results in higher revenue and more investment in AI.

  The video explicitly addresses AI models in general and is aimed at an Intermediate audience.

• Baseten CEO Tuhin Srivastava on Custom Models, and Building the Inference Cloud
  1.5.2026, 15:07:25

  The video is a conversation with Tuhin Srivastava, founder and CEO of Baseten, an AI inference cloud. The main topics are capacity constraints for AI compute, the importance of inference, workload development, the future of open-source models, and scaling Baseten.

  Tuhin Srivastava explains that demand for AI inference has risen sharply as companies deploy AI across more areas. He emphasizes the importance of the application layer, which is protected by specific workflows and user signals that only certain companies can gather. He sees great future potential for AI applications, both for new companies and enterprises using AI in-house.

  Another focus is the development of open-source models. Srivastava emphasizes that customers want the best models and that costs are optimized only after capability is achieved. He views the use of open-source models from China positively but warns against dependence on a single vendor and emphasizes the need for the US to develop its own open-source models.

  Srivastava also discusses challenges in securing compute capacity and the strategic importance of inference. He emphasizes the importance of the software layer for inference service stickiness and the need to close the loop between inference and post-training.

  He also mentions the importance of multi-chip worlds and the need to understand the workloads to invest in, such as code agents and long-horizon agents.

  Closing Comment: The video explicitly addresses open-source models and specific tools like Bridge, Cursor, and Open Evidence. It is better suited for Intermediate and Advanced audiences.

• AI Replacing Jobs is the Wrong Narrative
  29.4.2026, 18:16:32

  The video discusses the impact of AI tools like Codex and Cloud Code on the workplace, particularly in finance shared service centers. It argues that these tools will elevate the work of developers and other professionals to a higher level. Instead of writing code themselves, they will increasingly take on tasks like supervision, feedback, code reviews, and planning future requirements. Every role and level will be “upleveled” as routine daily tasks are delegated to AI agents. The focus shifts toward more strategic and creative activities.

  The video explicitly addresses AI tools like Codex and Cloud Code and is aimed at Intermediate and Advanced audiences.

• The One Constant in Software
  25.4.2026, 17:54:42

  In the 1970s, when SAP’s founders were still working at IBM, they repeatedly implemented financial systems for different customers. They quickly recognized that this approach was not economically scalable. Instead, they developed a solution that could manage companies end-to-end, from mainframes to client-server systems to the internet, mobile devices, and now AI. Although software has evolved over time, the core goal of customers remains the same: achieving concrete results. AI is now being used as a technology to achieve these results more efficiently while simultaneously redesigning the entire system.

  The video addresses SAP and AI in an enterprise context, better suited for Intermediate or Advanced audiences.

• SAP: Bringing the ‘Operating System’ of a Company into the AI Era with CTO Philipp Herzig
  23.4.2026, 10:00:18

  The video is an interview with Philipp Herzig, CTO of SAP, in which he discusses SAP’s AI strategy, the challenges of scaling, the importance of AI for business models, and the future of enterprise software. Herzig emphasizes that SAP has endured through multiple technology cycles because the company has focused on delivering results for customers. He explains that SAP offers the broadest range of enterprise software applications and platforms, ranging from financial and HR systems to supply chain and logistics management. Herzig also discusses the integration of AI into SAP’s products and the need to design AI in a scalable and secure manner. He mentions that SAP has already introduced products like “Joule for Consulting,” which can improve consultant efficiency by 30%. Herzig sees three main areas where AI will massively change enterprise software: user interfaces, business processes, and the data layer. He emphasizes that the greatest challenge is designing AI to deliver the right results within the enterprise. Herzig also talks about the importance of verifiable results and the need to design AI so it can be integrated with existing systems and data. He sees great opportunities in combining structured and unstructured data to make better decisions and automate business processes. Herzig believes that AI will fundamentally change how companies operate by automating repetitive tasks and enabling employees to focus on more strategic work. He sees SAP well-positioned to benefit from this change because the company focuses on delivering results for customers and has a flexible architecture that enables AI integration. Herzig emphasizes that the biggest challenges for enterprises in AI adoption are data integration, solution scaling, and system security. He believes SAP is well-positioned to address these challenges because the company offers a broad range of applications and platforms already in use at many enterprises.

  The video explicitly addresses SAP and OpenAI and is better suited for Intermediate and Advanced audiences.

Nic Conley (2 new videos)

• How I'd Actually Sell AI to Small Businesses in 2026 (Twin.so Tutorial)
  19.5.2026, 15:56:56

  The video introduces the Twin tool, promoted as particularly useful for building AI agents. The creator demonstrates how to create AI agents for various business processes with Twin without requiring deep technical knowledge. Three concrete use cases are demonstrated:

  1. **Facebook Marketplace Monitoring Bot**: An agent that searches daily for affordable lawn mowers near the user and sends an email with the results. The agent uses integrated tools like Appify and Perplexity to complete the task without requiring the user to set up separate APIs or subscriptions.

  2. **AI Readiness Quiz**: A questionnaire that helps small businesses assess their readiness for implementing AI technologies. The agent creates a personalized report with recommendations for suitable AI tools and saves the results for the user.

  3. **Cash Buyer Builder**: An agent that searches county deeds for recent cash purchases to create a list of potential buyers for real estate investors. The agent collects contact information and displays it in a dashboard.

  The creator emphasizes Twin’s simplicity and efficiency, as it requires no complex setup processes and already has many tools and integrations built in. He sees great potential in offering such agents to small businesses and building a business around them.

  **Final Note**: The video explicitly focuses on the Twin tool and is geared toward intermediate and advanced users.

• Easiest Hermes Agent Setup (better than OpenClaw)
  21.4.2026, 13:38:32

  The video compares two open-source AI agents: OpenClaw and Hermes, developed by Nous Research. The main difference is that the Hermes agent features a built-in learning loop that makes it smarter over time and adapts its capabilities to the user’s workflow. In contrast, OpenClaw often forgets previous tasks and starts fresh each session, which can be frustrating. Both agents can run on personal machines or a VPS and be accessed through chat apps like WhatsApp or Telegram. However, OpenClaw has a larger ecosystem with over 247,000 GitHub stars and more than 700 community skills, while the Hermes agent is ready to use out of the box and already includes 40 integrated tools. Another advantage of the Hermes agent is its higher security, as the integrated skills don’t come from third parties and are therefore less vulnerable to malware. The Hermes agent is a newer project that hasn’t been tested as extensively as OpenClaw. The video also demonstrates how to set up the Hermes agent on a VPS and connect it to Telegram to use as a personal assistant. The Hermes agent can automate tasks typically handled by an employee, such as researching events for a newsletter. The Hermes agent suits intermediate and advanced users seeking a powerful, learning-capable AI solution, while OpenClaw is better suited for tech-savvy users who prefer a larger ecosystem and more customization options.

Tech With Tim (10 New Videos)

• Stop jumping straight into building and spend 10 minutes planning first 🧠
  19.5.2026, 19:17:02

  The video addresses the neglect of the Software Development Life Cycle (SDLC) in modern software development. Many developers skip fundamental phases like planning, user story creation, requirements analysis, and technology stack decisions, jumping directly into development. This often leads to problems when the chosen architecture proves unsuitable for future features. The speaker emphasizes the importance of investing time in pre-planning and asking yourself the questions you would ask an external developer before starting implementation.

  The focus is on the significance of planning and foundational SDLC phases to avoid long-term issues. The video targets developers who want quick results but skip the fundamental steps of software development.

  Final comment: The video addresses general software development principles and is intended more for intermediate and advanced developers who already have experience with rapid development cycles.

• Did you know you can swap any two variables in Python without a temp variable? 🔥
  18.5.2026, 23:04:20

  The video showcases some fun Easter eggs in Python. When attempting to import the `braces` module from the `future` or `__future__` module, you get a custom exception with the message “not a chance”. Another example is importing the `anti-gravity` module, which opens a webpage with a Python-related comic. These Easter eggs are little surprises meant to give programmers a chuckle.

  The video focuses on Python and is more suitable for intermediate or advanced users.

• Did you know you can join any Python list into a string in just one line? 🔥
  18.5.2026, 14:00:02

  The video explains how to create a comma-separated string from a list or iterable object by using the `join` method. A separator (in this case, a comma and space) is defined to connect the list elements. Since the list may contain non-string values, the `map` function is used to convert all elements to strings before joining them with `join`. The example demonstrates how to convert a list of numbers into a comma-separated string.

  The video covers basic Python methods like `join` and `map` and is more suitable for beginners.

• Devin AI Is the Future of Coding… Full Tutorial
  18.5.2026, 13:02:48

  The video provides a comprehensive guide to Devin, an AI tool for software development that can run both locally and in the cloud. It starts with installing and setting up Devin for Terminal, a CLI-based tool that runs in your local development environment. Users can leverage Devin for simple tasks like creating a landing page or modifying code. The tutorial shows how to select different models, manage sessions, and use Subagents to handle parallel tasks.

  Next, Devin Cloud is introduced, which executes tasks on a virtual machine in the cloud. Users can offload tasks from their local environment to the cloud, handling long-running or complex tasks without burdening their local machine. The video also demonstrates how Devin integrates with GitHub to create and review pull requests, and how it connects with Linear and Slack to manage tasks directly from those platforms.

  In summary, the video shows how Devin can be used as a complete ecosystem for software development, from local code editing to automated task processing in the cloud. It’s particularly useful for developers looking to boost productivity and automate repetitive tasks.

  The video explicitly covers Devin (Cognition), a tool suitable for intermediate and advanced users.

• Mid level AI engineers are making up to $220,000 a year and demand is only growing 🔥
  16.5.2026, 15:45:02

  The video discusses salary structures and demand for mid-level Machine Learning (ML) professionals. The salary range spans from $155,000 to $220,000 per year. Engineers with 3 to 5 years of practical experience are particularly in demand because they can implement production models independently without supervision. These employees are more cost-effective than senior or staff engineers, making them attractive to many companies. However, there is high demand and low supply, driving strong growth in this field. Tasks include working on production AI systems, integrating Large Language Models (LLMs) into real-world applications, and collaborating with various teams. A central focus is how to deploy, scale, and implement models in real environments, not just in notebooks.

  The video covers general market trends and salary structures in the ML field without mentioning specific AI tools or models, and is directed at intermediate-level professionals.

• monday.com’s AI Agents Are Actually Insane
  16.5.2026, 12:00:10

  The video introduces two new AI agents from monday.com that automate project work. The first agent, the “Project Analyzer”, functions as a tireless project manager, organizing sprints, prioritizing bugs, mapping task dependencies, and creating stand-up summaries. It can even forecast delays and conflicts. The second agent, the “Research Assistant”, automatically gathers data from the web, such as competitive analyses and market trends, and delivers clean summaries. Both agents leverage the full context of your business processes, making their outputs specific and relevant. The video particularly recommends project managers and development teams try out the Project Analyzer.

  (Explicitly mentioned: monday.com; Target audience: Intermediate to Advanced)

• Every great AI engineer is a software engineer first 💻
  15.5.2026, 18:01:00

  The video argues that many people entering AI software development neglect fundamental software engineering principles. They often skip theoretical foundations and jump directly into AI development without first learning to write clean code or acquiring basic programming skills. This leads to messy scripts, missing tests, lack of version control, and unstructured workflows, ultimately causing deployment problems. AI engineering is presented as a specialization within software engineering, where traditional software engineering tasks like setting up APIs, backend services, writing tests, code reviews, and deployment management are crucial. Without knowledge of clean Python code, Git, and project structuring, developers will hit long-term obstacles and fail to build useful applications.

  The video covers fundamental software engineering principles and is more suitable for intermediate and advanced users.

• AI Web Scraping Is Insanely Good | Browserbase Full Tutorial
  15.5.2026, 15:19:07

  The video introduces Browserbase, a platform that connects AI agents with remote browser sessions to perform web automation. Browserbase offers an alternative to traditional tools like Playwright or Selenium by providing an AI-powered interface that uses natural language for automating browser actions. The platform solves many typical web automation issues, such as IP bans, rate limits, and CAPTCHAs, by using an agent identity that works with Cloudflare and other CAPTCHA providers. The video shows a step-by-step guide on how to integrate Browserbase with AI agents like Claude Code or Open Claw, as well as code examples in Python and TypeScript demonstrating the use of the Stagehand SDK. Various features are demonstrated, including extracting information, observing actions, and executing complex workflows. The benefits of Browserbase are highlighted through comparisons with traditional automation tools, particularly the ability to reliably automate dynamic and complex websites.

  The video explicitly covers the tools Browserbase and Stagehand SDK and is more suitable for intermediate and advanced users.

• This is how Codex turns raw data into a full CEO presentation in minutes 🤯
  14.5.2026, 15:30:12

  The video demonstrates how to use Codex, an AI tool, to research, analyze, and visualize data, as well as create a presentation. Specifically, it shows how to research the top 100 tech and AI creators, compile their average views, subscriber counts, and other key information in a table, and then create various charts and graphs. It then demonstrates how to transform this data into a five to seven-page PowerPoint presentation suitable for presenting to a CEO. The resulting presentation is well-formatted and appears professional, even if not perfect.

  The video explicitly covers Codex and is more suitable for intermediate users who already have basic knowledge of using AI tools.

• Every great AI engineer is a software engineer first 💻
  20.5.2026, 23:32:37

  The video addresses how aspiring AI engineers neglect fundamental software engineering principles. Many jump directly into working with AI without first learning to write clean code or acquiring basic software development skills. While they can hack together simple scripts for API calls, these are often unstructured, lacking task management, version control, or clear architecture. When it comes to deployment, they encounter massive problems. According to the video, AI engineering is merely a specialization within software engineering, not an entirely new discipline. The bulk of the work consists of traditional software engineering that happens to interact with AI models. This includes setting up APIs, backend services, writing tests, conducting code reviews, and managing deployments. Without clean Python code, Git knowledge, and experience structuring projects, you’ll hit limitations and fail to create anything useful.

  The video covers no specific AI tools or models and is directed at intermediate-level listeners who already have initial experience with AI but still need to improve fundamental software engineering skills.

NeuralNine (10 new videos)

• Pixi: The Package Manager For Everything
  18.5.2026, 16:01:32

  The video introduces Pixi, a system-wide package management tool for Linux, Mac, and Windows that manages both language packages (e.g., Python, Rust) and system dependencies (e.g., FFmpeg, OpenSSL). Pixi is based on Conda-forge and offers features like lock files for reproducible environments. The tutorial section covers Pixi installation, project creation, adding dependencies (Python, Pillow, ImageMagick), and using them in a Python script. It also demonstrates how to use Pixi for Rust extensions in Python without needing separate tools like Cargo or pip. Finally, it shows how to create custom tasks in Pixi to simplify long commands. The speaker emphasizes Pixi’s advantages over other package managers, particularly unified dependency management and creating reproducible environments.

  Closing comment: The video explicitly covers Pixi, which is based on Conda-forge and written in Rust. It’s geared toward intermediate and advanced users who already have experience with package managers and various programming languages.

• Fully Autonomous n8n Coding Agent
  17.5.2026, 10:16:17

  The video demonstrates two n8n workflows that automate GitHub, Slack, and a local script integration. The first workflow is triggered when a GitHub issue is created, executes a script on the user’s PC, and sends a success message via Slack. The second workflow takes a Slack message, processes it through an AI agent, creates a GitHub issue from it, and sends a confirmation message. In the demonstration, a GitHub issue is created requesting the first 10 Fibonacci numbers to be added to the readme.md. The user then receives a Slack message and a pull request with the implemented change. The second workflow shows how a Slack message is converted into a GitHub issue that creates a minimal Flask application.

  The video explicitly covers n8n and is geared toward intermediate users already familiar with workflow automation.

• This is the most useful n8n workflow I have ever built…
  15.5.2026, 16:00:28

  The video shows how to create a fully automated AI coding agent with N8N, Claude Code (Anthropic), OpenAI, and GitHub. The agent can be addressed via Slack or GitHub issues to make changes to a repository, commit them, and create a pull request. The process involves two N8N workflows: one for GitHub issues and one for Slack messages. The first workflow is triggered by creating a GitHub issue, runs a Python script that uses Claude Code in headless mode to implement the changes, and sends a success message via Slack. The second workflow takes a Slack message, converts it with an OpenAI agent into a GitHub issue, and triggers the first workflow. The video covers N8N setup, workflow creation, and integration of GitHub, Slack, and AI agents.

  The video explicitly covers N8N, Claude Code (Anthropic), OpenAI, GitHub, and ngrok. It’s suitable for intermediate and advanced users.

• JavaScript Crash Course: Full Beginner Tutorial
  13.5.2026, 16:01:18

  The video offers a comprehensive introductory course in JavaScript, focusing on the fundamentals of the programming language rather than its use in HTML for animations. It covers the following topics:

  1. **Introduction and Setup**:
  – Installing Node.js to run JavaScript files.
  – Creating a simple “Hello World” application with `console.log`.

  2. **Variables and Data Types**:
  – Defining variables with `let`, `var`, and `const`.
  – Differences between `let` and `var` (block vs. global scope).
  – Basic data types like numbers, strings, booleans, and special values like `undefined`, `null`, `Infinity`, and `NaN`.

  3. **Operators**:
  – Arithmetic operators (addition, subtraction, multiplication, division, modulo, exponentiation).
  – Assignment operators and increment/decrement operators.
  – Comparison operators and logical operators.

  4. **Conditional Statements**:
  – `if-else` statements and `switch-case` statements.
  – Processing user input with the `readline` library.

  5. **Loops**:
  – `while` and `do-while` loops.
  – `for` loops, including iterating over arrays.
  – Loop control statements like `continue` and `break`.

  6. **Functions**:
  – Defining and calling functions.
  – Parameters and return values.
  – Anonymous functions, lambda expressions, and functions with variable numbers of parameters.
  – Functions as first-class objects and callbacks.

  7. **Data Structures**:
  – Arrays: creating, accessing elements, and iteration.
  – Maps (dictionaries): key-value pairs and accessing values.
  – Sets: simple collection of unique values.

  8. **Objects and Classes**:
  – Defining objects with shorthand notation and with classes.
  – Using constructors and methods.

  9. **JavaScript in HTML**:
  – Embedding JavaScript in HTML files and interacting with the DOM.

  The video is suitable for beginners who have basic programming knowledge and want a quick overview of JavaScript as a programming language. No specific AI tools or models are discussed.

• ONNX: The PDF Format For Neural Networks
  11.5.2026, 16:00:44

  The video introduces ONNX (Open Neural Network Exchange), which serves as a PDF-like format for neural networks. The author demonstrates how to train models in PyTorch and TensorFlow, export them to ONNX format, and then use them with ONNX Runtime without the original frameworks. Both simple and more complex models, such as an MNIST classifier, are demonstrated. It also shows how to download and use models from Hugging Face in ONNX format. The focus is on reducing dependency on specific frameworks and increasing interoperability.

  **Closing comment:** The video covers ONNX, PyTorch, TensorFlow, Hugging Face, and ONNX Runtime and is suitable for intermediate users.

• Why you should start creating tech content…
  10.5.2026, 11:04:45

  The video lists three main advantages of teaching and sharing knowledge in technology. First, teaching forces deep understanding of the subject matter, as you need to explain concepts clearly and simply—similar to the Feynman Technique. You can also combine learning new technologies with teaching to continuously expand your skill set. Second, a portfolio of videos, blog posts, or GitHub repositories signals initiative and discipline, which is particularly valuable during uncertain job markets. It can even help bypass application processes. Third, having a certain reach opens doors, as a large audience is often associated with expertise and trustworthiness, leading to more offers and collaborations. The speaker emphasizes that while this shouldn’t be the primary motivation, it’s an important side effect.

  The video doesn’t discuss specific AI tools or models and is aimed at intermediate and advanced tech enthusiasts considering sharing their knowledge.

• OpenClaw: Simple VPS Setup Guide
  8.5.2026, 16:00:03

  The video provides a step-by-step guide to setting up Open Claw on a virtual private server (VPS) running Ubuntu. The focus is on speed and simplicity, with installation and Telegram connection at the center. The process includes updating the system, installing Node Version Manager (NVM) and Node.js, installing Open Claw via npm, and performing the onboarding process. OpenAI is selected as the model provider and Telegram as the communication channel. The user creates a bot via the Telegram Bot Father and connects it to Open Claw. After setup, the bot’s functionality is demonstrated by creating and editing a shopping list. The video warns about Open Claw’s security risks and recommends running it in an isolated environment.

  The video explicitly covers Open Claw, OpenAI, Telegram, and NVM, and is geared toward intermediate users.

• Coding Slack Bots in Python: Quick Start Guide
  4.5.2026, 16:00:21

  The video shows how to create a simple Slack bot with Python that can respond to messages and execute commands. The focus is on quickly implementing a Minimum Viable Product (MVP). Here are the main steps:

  1. **Creating a Slack App**:
  – Signing up at Slack and creating a new app via the Slack API.
  – Enabling Socket Mode and assigning necessary permissions.
  – Generating and storing the Socket token in a `.env` file.

  2. **Creating a Bot Token**:
  – Adding bot token scopes for chat functionality.
  – Enabling Event Subscriptions to respond to messages.
  – Creating a Slash Command (e.g., `/add` for simple calculations).
  – Installing the app in the Slack workspace and storing the bot token in the `.env` file.

  3. **Setting up the Python Project**:
  – Installing required packages (`python-dotenv` and `Slack-Bolt`).
  – Setting up the `.env` file with Slack tokens.

  4. **Implementing Bot Functionality**:
  – Simple response to the “hello” message with the username.
  – Implementing the `/add` slash command for simple addition.
  – Responding to general messages with a default response.

  5. **Connecting the Bot to a Language Model**:
  – Installing the `openai` package.
  – Integrating GPT-4O to respond to bot mentions and generate answers.
  – Updating Event Subscriptions for the mention feature.

  The video concludes with a demonstration of how the bot responds to mentions and answers questions, including generating Python code.

  **Closing comment**: The video explicitly covers using OpenAI (GPT-4O) and is geared toward intermediate users.

• How to stay up-to-date in AI/ML?
  3.5.2026, 22:40:53

  The video offers strategies to stay efficiently informed about current developments in AI and machine learning. The author recommends investing about 15 minutes daily to follow relevant news. This includes reading Hacker News, following YouTube channels like “Fire Ship” for quick updates and “AI Explained” for in-depth analysis, and engaging with communities and peers. These methods enable you to filter relevant information and receive it targeted, without being overwhelmed by information overload. The author emphasizes that this routine is sufficient to stay informed about the most important news.

  The video doesn’t discuss specific AI tools or models and is aimed at intermediate users who already have basic knowledge of AI and machine learning.

• Wagtail: The Django CMS For Blogging in Python
  20.5.2026, 16:00:05

  The video is an introduction to Wagtail, a Python-based content management system (CMS) built on Django. Wagtail is described as the “Arch Linux way” of CMS because it’s highly customizable and requires defining almost everything from scratch, unlike WordPress which provides many features out of the box. The tutorial covers Wagtail installation and basic configuration, including creating a new project, defining page models, customizing templates, and using the admin panel for content creation. It demonstrates how to create a blog structure with different pages and content, including integrating rich-text fields, code blocks, and snippets for authors. The video concludes by introducing an official Wagtail template as an example of a finished project.

  The video explicitly covers Wagtail and is geared toward intermediate to advanced users who already have basic knowledge of Django or similar frameworks.

Bart Slodyczka (5 new videos)

• What is Local AI and is it good? #localai #opensource #aiagents
  5.5.2026, 02:00:45

  The video explains the differences between cloud AI and local AI. Cloud AI, such as ChatGPT or Claude, processes requests on external servers, which raises privacy concerns and causes costs. Local AI, on the other hand, is installed on your own device and processes data offline, offering privacy and cost savings, but often comes with slower and less powerful models. The speaker emphasizes that local AI can be useful for private or business purposes, but for many applications, the more powerful cloud AI models are preferable.

  The video discusses Claude, ChatGPT, and local models such as Gemma 4, and is more suitable for intermediate users.

• LM Studio Is Getting Insane — Start Using It Now
  4.5.2026, 11:31:00

  The video demonstrates how to run AI models locally on your own computer using LM Studio. LM Studio is a free desktop app that allows you to search, download, and use various AI models. The video explains how to check your computer’s compatibility with the models, download models, and load them into LM Studio. It demonstrates how to communicate with the models through a chat-like interface, upload PDFs, analyze images, and perform web searches. Additionally, it shows how to integrate the models with other business tools such as Claude Cowork, Claude Code, OpenClaw, or Hermes Agent. The difference between cloud AI and local AI is explained, with local AI being private and free but often slower and less powerful. The video also covers technical aspects such as using Node.js and configuring MCP Tools (Model Context Protocol) for integrating external tools. Finally, it shows how to integrate a local AI model into the Claude Cowork app.

  The video explicitly discusses LM Studio, Gemma 4, Claude, Node.js, and MCP Tools, and is more suitable for intermediate users.

• Claude Cowork + Ollama = 100% FREE & PRIVATE (Full Setup)
  25.4.2026, 11:55:24

  The video shows how to use Claude Cowork for free and privately by using local AI models on your own computer or accessing Open Router to use cloud-based models. The creator demonstrates the use of the Gemma 26B model (18 GB, 256K context window) and the smaller Gemma E2B model (7.2 GB). For local use, Ollama is used to download and manage models. If your computer is not powerful enough, you can use Open Router, which provides access to hundreds of AI models, although with potential privacy concerns. The creator shows how to connect the Claude Desktop App with Ollama and Tailscale to establish a secure HTTPS connection. Next, it explains how to set up Skills, Connectors, and Plugins in Claude Cowork, including the integration of Brave Web Search. The creator tests both local and cloud-based models and finds that cloud models are faster, but may not interact as well with the app’s Skills. The video is suitable for intermediate users and discusses Claude, Ollama, Open Router, Tailscale, and specific tools such as LM Studio.

• Full Tutorial: How To Automate 99% Of Your Work With Claude Cowork
  22.4.2026, 13:03:14

  The video shows how to use Claude Cowork as a virtual assistant to automate 99% of your tasks. It begins with installing the desktop app and selecting a paid plan, with the Pro monthly option at $20 recommended. The user is guided through the app’s features, including the differences between Claude Chat, Claude Cowork, and Claude Code. Claude Cowork can access local files, work with Excel and Word documents, control the browser, and connect with tools like Gmail or ClickUp.

  The main focus is on how to use Claude Cowork effectively by changing the way you communicate with it. Instead of viewing it as a chatbot, you should think of it as a virtual assistant that can handle complex tasks such as writing emails or managing tasks in a task manager. The user is instructed to create projects and tasks, with projects serving as folders on the computer where all resources and generated files are stored. It emphasizes that providing context and background information is crucial to increasing the assistant’s effectiveness.

  The video also shows how to create Scheduled Tasks to automate repeated tasks, such as searching for the cheapest flights and recording the prices in an Excel spreadsheet. Finally, the use of Live Artifacts is demonstrated to display data from an Excel spreadsheet in an interactive dashboard.

  **Final note:** The video explicitly discusses Claude (Cowork, Chat, Code) and is more suitable for intermediate users.

• Best way to use Claude Code in 2026 #claude #coding #aicode
  22.4.2026, 08:27:35

  The video showcases the new features of the updated Claude Desktop App, which is now the most popular place to use Claude Code. Highlights include a detailed overview of token consumption per session and weekly limits. The app provides a preview tab to view websites or apps in real-time, as well as a diff view to track code changes. An integrated terminal enables running commands or starting additional Claude Code Agents. There is also an enhanced task view that displays sub-agents, and a plan mode for complex tasks. The app also enables voice control for more efficient work and provides detailed insights into token and model usage.

  The video explicitly discusses the Claude Desktop App and is more suitable for intermediate users.

AI Explained (2 new videos)

• GPT 5.5 Arrives, DeepSeek V4 Drops, and the Compute War Intensifies
  24.4.2026, 18:45:02

  The video provides a detailed summary of the latest developments in the AI world, particularly the release of GPT-5.5 and DeepSeek V4. GPT-5.5, which doesn’t yet have API access, shows mixed results across various benchmarks. It outperforms Opus 4.7 and Mythos Preview in some areas, such as agentic coding, but performs worse in others, like SWEBench Pro and Humanity’s Last Exam. OpenAI emphasizes the importance of intelligence per token and the model’s efficiency. DeepSeek V4, a Chinese model, supports a context length of one million tokens and is comparable to GPT-5.2 and Gemini 3 Pro in many benchmarks, but significantly cheaper. The video also discusses GPT-5.5’s capabilities regarding hallucinations, cyber security, and the ability to handle self-directed tasks. It notes that GPT-5.5 performs better in some areas like healthcare diagnostics and spreadsheets, but worse in others, such as chain-of-thought control. DeepSeek V4 also demonstrates strong performance in long contexts and specialized tasks. The video concludes with reflections on AI’s impact on productivity and the workforce, as well as challenges posed by compute scarcity.

  The video explicitly covers OpenAI (GPT-5.5), DeepSeek (DeepSeek V4), and Anthropic (Opus 4.7) and is geared toward intermediate to advanced users.

• Two Rival Bets on AGI: Google I/O Highlights
  20.5.2026, 16:50:34

  The video analyzes the key moments and statements from Google’s AI event and places them in the context of current developments in AI. Here are the central points:

  1. **Gemini Omni**: Google introduced Gemini Omni, a model that can transform various inputs into different outputs, including video, image, and speech. The quality of generated videos is compared to the Chinese model Seed Dance 2. Google emphasizes that such world models are an important step toward artificial general intelligence (AGI).

  2. **Different Approaches to AGI**: While Google bets on multimodal world models, OpenAI believes that text-based models are sufficient to achieve AGI. OpenAI has meanwhile shifted its video generation technology Sora to its robotics division.

  3. **SynthID**: Google and OpenAI are collaborating with SynthID to identify generated or edited images. This demonstrates cooperation between the two companies in certain areas.

  4. **Military Use**: Google, like OpenAI, has signed a contract with the Pentagon for the use of AI in military applications.

  5. **Gemini 3.5 Flash**: The new model is fast and capable, but not significantly cheaper than existing models. It shows good results across various benchmarks, particularly in financial analysis and processing tables and diagrams.

  6. **Agents and Applications**: Google demonstrated various agent applications, including a task that continuously searches based on specific conditions. However, the use of agents is still not mature.

  7. **Jaggedness Problem**: A research paper shows that AI models can even believe information clearly marked as false. Google DeepMind researchers emphasize that this problem is profound and difficult to fix.

  8. **Future of AI**: There are different views on whether jaggedness remains a long-term problem or whether recursive self-improvement of models could provide a solution. Andre Karpathy has joined Anthropic to work on this technology.

  The video explicitly covers Google’s Gemini, OpenAI’s models such as GPT-4.1 and Sora, as well as Anthropic’s Claude Opus 4.7. It is geared toward an advanced audience already familiar with current developments in the AI industry.

Alex Finn (10 new videos)

• Hermes just got 10x better…
  19.5.2026, 13:30:10

  The video presents eight major updates for the Hermes Agent that significantly improve the tool’s functionality. The key new features include:

  1. **Session Recall**: Improved memory function that allows retrieving all previous conversations and actions without consuming tokens.
  2. **Background Tasks**: The ability to run multiple tasks simultaneously in the background, enabling true multitasking capabilities.
  3. **Grock 4.3 Integration**: Using the Grock 4.3 model for tasks like real-time Twitter search and video creation.
  4. **Native Codec CLI Usage**: Integration of Codec CLI for cost-effective and efficient coding.
  5. **Computer Control**: The ability to control the computer and autonomously perform tasks like calendar management.
  6. **Video Creation**: Native text-to-video and photo-to-video functions within the tool.
  7. **Automatic Kanban Task Distribution**: Automatic breakdown of tasks into subtasks and their distribution to different subagents.

  The video is best suited for intermediate to advanced users, as it presents detailed features and integrations that require some prior knowledge. It specifically covers Hermes Agent, Grock 4.3, Codec CLI, and Telegram.

• Claude Code is 1000x better when you use this tool
  17.5.2026, 18:06:00

  The video showcases an efficient workflow integration of Claude Code (or alternative vibe coding tools like Codeex, Cursor) with the project management tool Linear. Linear serves as a “second brain” by automatically organizing, prioritizing, and linking tasks (issues) to GitHub. This enables seamless collaboration between different devices and AI agents, reduces manual planning, and increases productivity. The creator demonstrates building a prompt library app, with Claude Code completing tasks from Linear, generating code, and testing independently. He also shows how GitHub branches are created for each task to facilitate code overview and review. A bonus tip is integrating Slack for team updates. The video is intended for intermediate to advanced users of AI coding tools and specifically covers Claude, Codeex, Cursor, Linear, and GitHub.

• LIVE: GROK BUILD CLI IS ACTUALLY INCREDIBLE???
  15.5.2026, 20:24:28

  ### Video Summary

  The video is a live stream session where the creator discusses various aspects of selling Software-as-a-Service (SaaS) while testing the capabilities of Grock Build, a tool by XAI. The stream begins with a casual introduction encouraging viewers to participate and chat. He discusses the importance of Twitter (X) for software sales and the need to build a community.

  He then covers the three key factors for SaaS product success: distribution, network effects, and partnerships with government data. He emphasizes that a strong community and good sales are crucial for success.

  A large portion of the video is dedicated to demonstrating and testing Grock Build, a new tool from XAI. The creator performs several benchmark tests, including creating a 3D first-person shooter, an Elon Musk animation, and a 3D city flythrough. He evaluates the results and compares them with other AI tools like Claude, OpenAI, and Gemini. While Grock Build performs well in some areas, there is also criticism regarding the tool’s user-friendliness and costs.

  The creator also shares personal experiences with various AI tools and expresses his views on the current landscape of AI development. He emphasizes the importance of coding skills for AI tool success and praises Anthropic for developing Claude Code.

  Towards the end of the video, the creator announces that he will do fewer live streams in the future and focus more on creating pre-recorded videos. He invites viewers to join his Vibe Coding Academy bootcamp, where he’ll discuss more about SaaS, AI investments, and his workflows.

  ### Final Comment

  The video specifically covers AI tools and models from Claude (Anthropic), OpenAI (ChatGPT, Codex), Gemini (Google), and specific tools like Grock Build (XAI). It is intended for intermediate and advanced users interested in SaaS development and sales as well as the latest developments in the AI industry.

• LIVE: The greatest Claude Code workflow ever
  13.5.2026, 20:12:33

  The video showcases a detailed, advanced workflow for Claude Code integrating various tools like Slack, Linear, GitHub, and Claude Code. The host explains how these tools work together to increase productivity, track changes, and organize development. The workflow includes creating tasks and projects in Linear, linking to GitHub for branch management, and using Claude Code to automate and manage these processes. The host emphasizes the benefits of this workflow, such as increased speed, better error prevention, and improved traceability.

  Additionally, the host discusses personal experiences and challenges, such as dealing with difficult times and the importance of perseverance. He also shares his thoughts on using AI tools like Claude Code and Codex, as well as their differences and use cases.

  The video is intended for advanced users who already have experience with Claude Code and similar tools and want to optimize their workflows. It specifically covers Claude, OpenAI, and Linear.

• Hermes Agent powered by local models on the DGX Spark is basically magic
  13.5.2026, 13:30:07

  The video demonstrates how to set up a Hermes Agent on a local model on an Nvidia DGX Spark to create a 24/7 available AI employee. The process includes setting up the DGX Spark in headless mode, installing a local model (Quen 3.6 27B), and integrating the model into the Hermes Agent. The creator demonstrates three use cases: a daily report on AI stocks for beginners, repurposing YouTube video content for intermediate users, and vibe coding a to-do list app for advanced users. The focus is on the benefits of local models, such as being cost-free (apart from electricity), privacy, customizability, and educational value.

  Final Comment: The video specifically covers Nvidia DGX Spark, Hermes Agent, Quen 3.6 27B, and Tail Scale, and is intended for intermediate to advanced users.

• LIVE: Talking AI news (no Hermes use cases ignore the thumbnail)
  11.5.2026, 20:11:47

  The video is a live stream session primarily focused on discussing Hermes Agent and its use cases. The host, Alex Finn, begins with an introduction to Hermes Agent, emphasizing the importance of use cases for leveraging the technology. He mentions that Hermes has released a new website with hundreds of use cases that he and the viewers will go through and test.

  However, a large portion of the video is taken up by various tangents and discussions, including:

  1. **Investment Corner**: Alex discusses current investment opportunities in the AI industry, particularly in companies like Nvidia, Micron, TSMC, and Tesla. He emphasizes the importance of current AI developments and the need to invest in the right companies.

  2. **Personal Stories and Anecdotes**: Alex shares personal stories and anecdotes that are often humorous and entertaining but not directly related to the main topic of the video.

  3. **Chat Interaction**: A large part of the video consists of interacting with the live chat, with Alex answering questions, making comments, and engaging with viewers.

  4. **Hermes Agent Use Cases**: Towards the end of the video, Alex begins discussing some of the use cases from the new Hermes website. He mentions use cases like creating research reports, managing tasks, and automating processes.

  5. **Announcements and Updates**: Alex provides updates on his own projects and announcements, such as launching a second YouTube channel and attending a Baby Keem concert.

  **Final Comment**: The video specifically covers open-source AI models and tools like Hermes Agent and OpenClaw. It is intended for intermediate to advanced users who already have some understanding of AI and its applications.

• Hermes Agent is blowing me away…
  9.5.2026, 20:54:26

  The video compares the AI agents Hermes and OpenClaw, recommending Hermes for its reliability, self-improvement, and user-friendliness. The author describes the advantages of Hermes, including regular, thematic updates, a self-improving capability through usage, and strong emphasis on experimentation and local models. Installing Hermes is described as straightforward, with options for different models and communication services, with Telegram and Opus recommended. The author demonstrates three use cases: a beginner case discovering new AI tools daily, an intermediate case conducting daily proactive check-ins, and an expert case creating AI-generated videos. At the end, the author emphasizes the importance of brain-dumping and reverse-prompting to use the AI agent personally and effectively.

  The video specifically covers the AI tools Hermes Agent and OpenClaw and is intended for intermediate and advanced users.

• LIVE: Anthropic and Elon just teamed up to take down OpenAI
  6.5.2026, 20:12:34

  The video covers the strategic alliance between Anthropic and Elon Musk’s XAI (X.AI), characterized by a major computing power deal. Anthropic gains access to SpaceX’s Colossus-1 cluster, which will significantly enhance their ability to develop and train AI models. This partnership marks a turning point in competition with OpenAI, which has held a dominant position in recent months with Codeex. Anthropic has struggled during this time with reduced limits and less capable models, which the new alliance aims to address. Elon Musk, who was previously critical of Anthropic, now provides massive computing resources, changing the dynamics of AI competition. The video also discusses Elon Musk’s long-term strategies, which may focus on larger goals such as autonomous vehicles, space exploration, and robotics rather than staying in the AI chatbot competition. The alliance could lead to a new era of innovation and improvement in AI tools, benefiting consumers. The video emphasizes the importance of using both leading AI tools, Claude Code and Codeex, to benefit from their respective strengths.

  **AI Tools/Models/Providers:** Anthropic, OpenAI, Elon Musk (X.AI), Claude, Codeex, Grock, Gemini, Open Source
  **Target Audience:** Intermediate

• Hermes Agent might have just killed OpenClaw
  5.5.2026, 21:11:59

  The video presents Hermes Agent as a more reliable alternative to OpenClaw and covers seven new features that improve productivity and user-friendliness. These include:

  1. **Kanban Board**: Enables multitasking by processing multiple task threads in parallel. A manager agent populates tasks with details and moves them through various statuses (Triage, To-Do, Ready, In Progress, Blocked, Done).

  2. **Slashgo**: A high-level mission function that assigns long-term tasks to the agent that can be worked on over an extended period. The quality of the prompt is crucial for good results.

  3. **Profiles (Multi-Agents)**: Allows creating multiple agents with their own memories and capabilities to optimize performance and prevent overload.

  4. **Model Catalog**: Simplifies switching and assigning models to specific tasks, improving cost control and efficiency.

  5. **Compression**: By adjusting the compression threshold to 0.5, less drastic compressions are performed, improving memory capability.

  6. **Curator Feature**: Automatic pruning of rarely used skills every seven days to reduce bloat and maintain performance.

  The video criticizes OpenClaw for frequent updates that lead to instability and performance issues, highlighting Hermes’ targeted, reliable updates. It recommends leveraging Hermes’ new features to increase productivity.

  **Final Comment**: The video specifically covers Hermes Agent and OpenClaw and is intended for intermediate to advanced users.

• LIVE: Is Hermes better than OpenClaw? FINALE!!!
  4.5.2026, 21:53:53

  The YouTube video shows a live stream in which the host tests various AI agents (OpenClaw and Hermes) in a competition called the “Agent Olympics.” The stream is unusually long (3.5 hours) and is divided into different sections, ranging from technical tests to personal discussions to spontaneous decisions.

  **Content Summary:**
  1. **Agent Olympics:**
  – The host tests four combinations of AI agents (OpenClaw and Hermes with different backend models like ChatGPT and Opus) on five different tasks.
  – The tasks include creating infographics, animated music videos, and other complex assignments.
  – Results are evaluated live, with OpenClaw using Opus ultimately emerging as the winner.

  2. **Technical Discussions:**
  – There are extensive discussions about the stability and reliability of different AI agents, particularly Hermes, which is criticized for “compaction” errors (loss of work states).
  – OpenClaw is praised for its consistency and user-friendliness.

  3. **Personal Topics:**
  – The host discusses his sleep problems and experiments with various solutions like kiwis and magnesium.
  – There are discussions about work methods, including the use of treadmills and standing desks, with the host expressing his preferences and dislikes.

  4. **Community Interaction:**
  – Viewers are actively engaged in the chat, asking questions and providing feedback.
  – The host spontaneously decides to create a second YouTube channel called “Alex Finn Labs,” leading to an entertaining interaction with a viewer who has already reserved the desired channel name.

  5. **Announcements and Future Plans:**
  – The host announces that he will publish more videos about Hermes and multi-agent setups in the future.
  – There is discussion about whether live streams should take place at later times to reach a broader audience.

  **Final Comment:**
  The video specifically covers the AI tools OpenClaw, Hermes, ChatGPT, and Opus. It is intended for intermediate and advanced users, as it covers technical details and advanced applications of AI agents.

AI Foundations (2 new videos)

• Full Hermes Agent Set-Up For Beginners in 2026! (24/7 AI Agent)
  12.5.2026, 14:56:27

  This video is a tutorial on setting up the Hermes Agent, a 24/7 self-improving AI agent that runs on a server and continuously learns from feedback. The agent consists of three layers: memory, skills, and cron jobs. Memory enables the agent to integrate learned knowledge into future sessions. Skills are automations or mini-workflows that the agent creates and improves. Cron jobs allow tasks to be scheduled at specific times. The agent goes through a loop where it sets goals, uses tools, delivers results, and improves through feedback.

  The author compares setting up the agent on a local computer with setting it up on a VPS (Virtual Private Server). A VPS is always online and scalable, whereas a local computer is only active when powered on. The VPS setup is described in detail, including using Hostinger for VPS deployment and setting up the agent via terminal. The agent can be used with various models such as Claude, OpenAI, or Open Router and can be controlled through different messaging platforms like Telegram.

  At the end, the author shows a practical example of how he uses the Hermes Agent to automatically create and publish blog posts based on his YouTube videos. The agent checks analytics, improves content, and can be controlled via Telegram.

  The video explicitly covers Hermes Agent, Open Router, Claude, OpenAI, and specific tools like Telegram. It’s intended more for intermediate and advanced users.

• FULL Claude Cowork Tutorial For Beginners in 2026! (Zero to PRO)
  4.5.2026, 17:28:28

  This video provides a comprehensive introduction to Claude Cowork, an advanced feature of AI Claude that goes beyond basic chat functionality. It begins by explaining the pricing structure, which requires at least Claude’s Pro version, and highlights the unique features of Cowork that are not accessible through the web interface but rather through a desktop application.

  The tutorial shows the Claude Cowork user interface and explains the various tabs such as Projects, Scheduled Tasks, Live Artifacts, Dispatch, and Customizations. A central focus is on the difference in interaction with Claude Cowork compared to chat mode. Cowork is designed to accomplish tasks, while chat mode is more suited for brainstorming and strategy development.

  A practical example demonstrates how to create a folder on the desktop and have Claude Cowork interact with it to conduct research on the year 1800. In doing so, subagents are deployed to research in parallel and create markdown files. This feature enables multiple tasks to be worked on simultaneously with results saved directly to the computer.

  Another important aspect is the creation of live artifacts, described as mini-applications connected to real-time data. An example shows how to create an interactive dashboard for the year 1800 that contains various information and learning tools.

  The video also demonstrates how to connect tools like Gmail with Claude Cowork to automate tasks such as categorizing invoices. This integration enables reading and writing data from various applications, greatly increasing efficiency when handling emails and other tasks.

  Additionally, Claude Skills are introduced, described as automations that perform specific tasks in the same way consistently. One example is a daily briefing automation that summarizes emails and calendar entries, giving the user an overview of the day.

  Projects in Claude Cowork are described as containers that hold specific instructions and files to accomplish particular tasks. An example shows how to create a project for generating SEO-optimized blog posts based on YouTube transcripts.

  The video concludes with an invitation to join the AI Foundations Community, where additional courses and resources for automation with Claude are offered.

  Final comment: The video explicitly covers Claude Cowork and is intended more for intermediate to advanced users.

n8n (6 new videos)

• From the n8n canvas to Microsoft Teams with Microsoft Agent 365
  19.5.2026, 16:32:30

  The video shows a live demo and step-by-step guide for setting up Microsoft Agent 365 in connection with the n8n automation platform. Here are the main points:

  1. **Introduction to Agent 365**: Agent 365 is a new node within the n8n automation system that enables you to create and manage agents with enterprise identity, permissions, governance, and Microsoft Copilot (MCP) tools in Microsoft 365.

  2. **Demo Steps**:
  – **Prerequisites**: Requires a Microsoft Copilot license, Teams license, Agent 365 license, and global administrator role in the Microsoft tenant.
  – **Microsoft-side setup**: Installation and use of the Agent 365 CLI tool to create an agent blueprint. This blueprint defines the name, description, developer information, and access rights to Microsoft tools like Outlook, Teams, and Word.
  – **n8n-side setup**: Integration of the Agent 365 trigger node in n8n, which establishes connections to a chat LLM model, a memory node, and various tools like Salesforce and ServiceNow.
  – **Publishing and usage**: The agent blueprint is published in Microsoft 365, and users can create agent instances via the Microsoft Agent Store. The demo shows how a sales team uses an agent to compile data for a quarterly business review.

  3. **Security and governance features**: Agent 365 offers comprehensive security and governance functions that enable IT administrators and security teams to monitor and control agent activities. This includes defining permissions, assigning user access, and real-time monitoring of agent activities.

  4. **Advanced use cases**: The demo shows how the agent can integrate with tools like PagerDuty to retrieve incidents and transfer them to an Excel spreadsheet, which is then shared via email. This demonstrates the agent’s ability to interact with various services beyond the Microsoft ecosystem.

  5. **Future developments**: Participants are encouraged to provide feedback and suggestions on how the platform can be further improved, particularly regarding simplifying the setup process and expanding use cases.

  The video explicitly addresses Microsoft Agent 365 and n8n, and is aimed at intermediate to advanced users who already have experience with automation platforms and Microsoft 365.

• n8n Desk: The Open Source Claude Desktop That Runs on top of n8n's new MCP
  11.5.2026, 18:03:38

  The video features a demonstration by Marcel, who introduces two new tools: the official n8n MCP (Meta-Cognitive Protocol) and n8n Desk, an open-source desktop application that works similarly to Claude Desktop but with some important differences. The n8n MCP allows AI agents not only to execute n8n workflows but also to create and edit them. This is a significant advancement, as previously it was only possible to execute workflows. Marcel demonstrates the creation of a support ticket agent that communicates via Slack. n8n Desk, on the other hand, does not execute code locally on the computer but uses n8n instances in the cloud, which is safer and better suited for enterprise environments. The application supports various AI models, including local models, and offers features like Co-Work, Workflow, and Chat. Marcel emphasizes the importance of context and Skills for effective use of AI agents and demonstrates how n8n Desk integrates these aspects. The video concludes with the announcement that n8n Desk will be available as an open-source project, with the opportunity to be notified via a waitlist.

  The video explicitly addresses n8n, Claude, and open-source tools, and is aimed at intermediate and advanced users.

• How we use n8n: Sindhuja, product leader
  4.5.2026, 14:17:20

  The video is an interview with Sindhuja, a Product Manager in the AI team at n8n. She shares her career journey, which has taken her from engineering to founding an EdTech company and ultimately to n8n. At n8n, she initially improved user adoption and retention before transitioning to the AI team to drive the use of AI for simplifying workflows. She discusses the development of an instance-level MCP that allows users to leverage n8n from various platforms, and emphasizes the importance of community feedback. She also uses n8n herself for personal and professional workflows, including an AI assistant within the product. She envisions n8n’s future in combining creativity and reliability to make automation accessible to everyone.

  The video explicitly addresses the tool n8n and is aimed at intermediate or advanced users.

• n8n Livestream: Product Updates, Community Creator & the latest Community Challenge
  30.4.2026, 16:30:56

  The video shows a livestream session with various updates and presentations around the n8n platform, a tool for workflow automation. Here are the key points:

  1. **Product Updates from Nick and David**:
  – **MCP (Multi-Cloud Platform)**: A tool for creating n8n workflows currently in beta and continuously being improved. It enables the integration of Coding Agents and other tools.
  – **Agents as First-Class Citizens**: Agents are treated as standalone entities alongside workflows, with enhanced features such as long-term memory, state management, and routing strategies.
  – **AI Assistant**: A new AI assistant capable of creating, testing, and iterating workflows. It has access to various tools such as browser, file system, and multimodal capabilities and is designed to proactively suggest improvements.
  – **n8n Connect**: A feature that enables direct consumption of AI tokens within n8n and facilitates access to various services like web search, web scraping, and OCR.

  2. **Community Member Zayn Khan**:
  – Presentation of a customer project that automates support ticket management with n8n. The workflow uses JotForm for input, AI agents for classifying tickets by severity and sentiment, and integrates databases like Airtable as well as Slack for notifications.

  3. **Community Challenge**:
  – Introduction of the monthly Community Challenge, where participants can solve real-world use cases with n8n. Winners are featured in the next livestream and their workflows are published in the official n8n template collection.
  – The current challenge focuses on “Human-in-the-Loop” automation, where human review steps are integrated into the workflow. An example was the review of social media content by various team members.

  4. **Additional Information**:
  – **Fridays for AI Days**: A weekly initiative where users can share their workflows and earn rewards.
  – **Job Openings**: n8n is hiring for new positions, particularly for community teams.
  – **Newsletter and Events**: Information about the monthly newsletter and upcoming community events, including a special event for women in automation.

  The video explicitly addresses n8n and its various features and tools, particularly MCP, Agents, AI Assistant, and n8n Connect. It is aimed at intermediate and advanced users who already have experience with workflow automation and want to deepen their knowledge.

• Create n8n Workflows With Agents | Official MCP
  29.4.2026, 14:18:27

  The video demonstrates how to use n8n’s new MCP interface (Multi-Tool Calling Protocol) to create and edit workflows with the help of AI models like Claude. The MCP interface allows you to create workflows directly in n8n without manually copying and pasting JSON code. The process includes connecting n8n with Claude via the MCP interface, configuring access rights, and using Claude Code to create workflows. The video also shows how to set up the MCP interface with other Coding Agents like Open Code. This tutorial provides guidance on setup and offers an outlook on future applications.

  The video explicitly addresses n8n, Claude, Claude Code, and Open Code, and is aimed at intermediate users.

• Why n8n + Lovable Is Replacing Salesforce, HubSpot, and Slack
  20.5.2026, 23:37:26

  The video is a podcast interview with Olaf, a representative of Lovable, a company focused on using AI for software development. Olaf discusses Lovable’s vision to democratize software development and enable everyone to create applications regardless of technical skills. He emphasizes that the limitation is no longer technical expertise but people’s ideas.

  Some of the main points of the interview are:

  1. **Lovable as Co-Founder**: Lovable is positioned as a co-founder for startups and entrepreneurs who want to develop software solutions quickly and cost-effectively.
  2. **Success Stories**: Olaf shares examples of users who have created successful applications with Lovable, such as an app that helps women check the criminal history of potential dates.
  3. **Integration with Other Tools**: Lovable integrates with various tools and platforms to facilitate the development and deployment of applications.
  4. **Future of Software Development**: Olaf discusses the future of software development and how AI will revolutionize the way we create and use software.
  5. **Security Concerns**: He raises concerns about security and responsible use of AI, particularly regarding access to sensitive data.

  The video explicitly addresses the AI tools and platforms Lovable, Claude, and open-source tools. It is aimed at intermediate and advanced users interested in integrating AI into software development.

Greg Baugues

No new videos in this period.

TheAIGRID (10 New Videos)

• 10 Best AI Tools For Business Owners in 2026 – How To Start Your Business With AI
  16.5.2026, 21:15:02

  The video presents 10 AI tools suitable for small businesses and beginners without technical knowledge. Here are the key points:

  1. **ChatGPT**: A versatile tool for tasks like email writing, brainstorming, document summarization, social media posts, and more. It’s particularly useful for small businesses to save time and overcome creative blocks. The Plus plan costs $20 per month.

  2. **Claude Co-work**: A desktop agent from Anthropic that can autonomously handle local files and applications. It can take on tasks like organizing files, creating presentations, and managing Excel spreadsheets. The base price is $20 per month.

  3. **Microsoft 365 with Claude**: Claude can be integrated into Microsoft Word and Excel to automate tasks like creating financial analyses and managing documents. It’s particularly useful for generating financial forecasts and managing data.

  4. **Copilot in Microsoft 365**: Built-in AI in Microsoft 365 that offers similar features to Claude but is less powerful. It’s a cost-effective alternative for businesses with limited budgets.

  5. **Gamma.app**: A tool for creating presentations and websites. It’s particularly useful for small businesses that want to create professional presentations and websites without design knowledge.

  6. **Google’s Pomelo**: A free marketing tool from Google that generates social media posts, advertising campaigns, and email banners based on a website URL. It’s particularly useful for businesses wanting to strengthen their brand identity.

  7. **Flow by Google**: An image generation tool particularly useful for businesses that regularly need to create images for marketing purposes. It offers 50 free credits to get started.

  8. **Canva AI**: A tool for creating marketing visuals that suggests layouts, generates images from prompts, and adapts designs for various social media platforms. It’s particularly useful for businesses wanting to maintain consistent brand identity.

  9. **Zapier**: A tool for automating workflows between different applications. It can automate tasks like creating calendar entries and managing customer inquiries. It offers a free version and paid plans up to $20 per month.

  10. **Chatbase**: A tool for integrating AI support agents into websites. It enables businesses to integrate automated customer support agents on their websites that can answer questions based on PDFs or Word documents with company knowledge. It offers a free version and paid plans starting at $32 per month.

  11. **Perplexity Computer**: An expensive but powerful AI agent tool that can automate tasks like creating reports, scraping websites, and managing data. It’s particularly useful for businesses wanting to automate complex tasks. The price is $200 per month.

  12. **Lovable**: A tool for creating AI-assisted websites. It’s particularly useful for businesses wanting to quickly and easily create a website without design knowledge.

  The video is suitable for small businesses and beginners without technical knowledge. It covers various AI tools and models, including ChatGPT, Claude, Microsoft 365, Copilot, Gamma.app, Google’s Pomelo, Flow by Google, Canva AI, Zapier, Chatbase, Perplexity Computer, and Lovable.

• Meta AI Tutorial – How To Use Meta AI
  13.5.2026, 21:15:04

  The video presents Meta AI’s features and tips for using it. It begins by explaining three chat modes: “Instant” for quick, casual questions, “Thinking” for more complex problems requiring deeper thought, and the secret “Contemplating” function that uses up to 16 independent agents for parallel analysis. This function is particularly useful for research, strategy development, and difficult decisions. Next, Meta AI’s search function is demonstrated, which pulls information from the open web and Meta’s social graph, including Instagram Reels and Facebook posts. Meta AI’s multi-modality is highlighted, particularly image analysis and visual grounding, which can provide detailed analyses and personalized health information from images. Analysis of PDFs, Excel, and Word documents is also mentioned. Additionally, image and video generation with Meta’s “Vibes” is presented, currently based on Midjourney, as well as the Meta Vibes social platform where users can share and remix AI-generated content.

  The video explicitly addresses Meta AI and is aimed at intermediate users.

• Google's New Gemini Omni Just Shocked Everyone – Leaked Demo, Pricing, and what comes next
  12.5.2026, 19:45:04

  The video covers the leak of a new Google AI video model called Gemini Omni, which was accidentally made accessible to some users. The discovery began with a tweet pointing to an unusual text line “powered by Omni” in the Gemini app. Users generated initial videos showing impressive quality comparable to current top models like Sora 2. The videos demonstrate complex scenes, such as a professor explaining a mathematical proof on a blackboard and a detailed restaurant scene with two people. Using the model is highly resource-intensive, with two generations already consuming 86% of a Pro subscription’s monthly quota ($20/month). The name “Omni” suggests a multimodal model supporting various input and output modalities, similar to the never officially released GPT-40. The video speculates on a potential Omni introduction at the upcoming Google I/O and compares it to current competitors like Sora 2, Alibaba’s W2.7, and Cline 3.0. It discusses whether Omni could be a standalone product or an evolution of VO4, with the potential to significantly change the AI video landscape.

  The video explicitly addresses Google’s Gemini Omni and compares it to other models like Sora 2 and GPT-40, targeting an intermediate to advanced audience.

• How To Use Claude For Microsoft Word (Microsoft Word Claude Tutorial)
  9.5.2026, 20:15:01

  The video shows how to use Claude in Microsoft Word. First, add-in installation is explained, noting that a Claude Pro or Max plan is required. Users are encouraged to use the Sonnet 4.6 or Opus 4.6 models, with Opus 4.7 reserved for mathematical tasks. Important settings like “Working Over Files” are highlighted, enabling context sharing across different Office files.

  The video demonstrates how Claude can be used in Word to write, edit, and format text. It shows how to highlight specific sections and then expand or rewrite them. Additionally, Claude’s ability to reformulate text in different styles and structures is emphasized, including adding headings and bullet points.

  Another focus is the ability to mark and analyze specific document sections, for example, to highlight security aspects or key points. The integration of web research directly in Word is also shown, with the note that this feature is only suitable for simple search queries.

  The video also shows how Claude can collaborate with other Office applications like Excel and PowerPoint to integrate data from these applications into Word documents. This is demonstrated with an example where sales data from Excel is incorporated into a shareholder letter.

  Finally, the use of templates in Word is shown, such as for resumes, with the note that Claude can sometimes have difficulties with complex formatting. It’s recommended to use the “Undo” function if problems occur or repeat the task with a higher-tier model.

  The video explicitly addresses Claude and is aimed at intermediate users.

• OpenAI Is Losing The AI War
  8.5.2026, 22:34:30

  The video analyzes the current state of competition between leading AI companies, particularly between OpenAI and Anthropic. It notes that Anthropic has significantly gained market share in recent months, both among private users and in the enterprise sector. Anthropic is recording unprecedented revenue growth and has overtaken OpenAI in many areas, particularly in usage for coding and general tasks. The frequent product releases and strong market position of Anthropic, particularly with models like Claude Opus and Mythos, are highlighted. Additionally, Anthropic’s dismissive stance toward certain government requests is presented as a positive PR moment that strengthened trust in the company. Investors are increasingly skeptical of OpenAI, while Anthropic is seeing high demand in the secondary market. The video concludes with the observation that user preferences have shifted significantly toward Anthropic, raising the question of whether OpenAI can still close this gap.

  The video explicitly addresses Anthropic, OpenAI, Gemini, and specific models like Claude Opus and Mythos. It is aimed at intermediate and advanced users wanting to familiarize themselves with current developments and market trends in the AI industry.

• Claude For Powerpoint Tutorial – How To Use Claude With Powerpoint
  7.5.2026, 21:00:59

  The video demonstrates the use of “Claude for PowerPoint,” an official add-on from Anthropic directly integrated into Microsoft PowerPoint. It enables generating fully editable PowerPoint elements based on existing templates or new content. The add-on is available in various pricing tiers but is still in beta/research phase.

  To use Claude for PowerPoint, you need a Claude Pro account (from $20/month) or a Max Team/Enterprise subscription, as well as a current version of Microsoft PowerPoint (Desktop or Web). After installation via the add-in function in PowerPoint, you can choose between two models: Opus 4.6 for complex tasks and Sonnet 4.6 for quick edits. Settings allow you to establish standards like fonts, colors, and notes for each slide. Important is the option to confirm changes beforehand to prevent unwanted edits.

  Claude automatically reads the template layouts, fonts, and color schemes and generates slides following the template’s visual structure. An important tip is to load the template before prompting, as Claude uses it as a reference. The video shows examples of creating presentations from text prompts, editing individual slides, converting PDFs and Excel data into slides, and generating presentations based on websites. Claude can also translate presentations into other languages and add speaker notes.

  Some limitations are mentioned, such as a 30 MB file size limit, potential issues with complex layouts, and limited graphic analysis capability. The add-on is currently only available for Desktop and Web, not for iPad or Android.

  The video explicitly addresses the AI tool “Claude for PowerPoint” from Anthropic and is better suited for intermediate users already familiar with PowerPoint who want to leverage AI tool functionality.

• Why AI Ceos Are Now Afraid Of AI
  6.5.2026, 21:15:05

  The video discusses the ambivalence and fears of the richest and most powerful men in the world working on artificial general intelligence (AGI). They see AGI as both humanity’s greatest opportunity and a potential end to civilization. A central problem is the alignment problem: How can one ensure that a superintelligent AI understands and follows human values and unspoken assumptions? So far, there is no solution. Additionally, there is growing fear of an AI arms race, as whoever develops AGI first gains a dominant position. This could destabilize existing economic and political structures. Another critical point is recursive self-improvement, where an AI could exponentially increase its own intelligence, leading to a sudden, difficult-to-control intelligence jump. Finally, the danger is emphasized that AGI could be used as a weapon, resulting in autonomous cyberattacks, biotechnological threats, and massive disinformation. Current developments are occurring without international regulation and controls, further increasing risks.

  The video explicitly addresses OpenAI, Anthropic, Safe Superintelligence Inc., and models like GPT-6, as well as Grok, and is aimed at intermediate and advanced viewers.

• How To Use Pomelli – Google Pomelli Tutorial –
  5.5.2026, 21:15:01

  The video introduces Google Labs’ new AI-powered marketing tool “Meli,” which generates social media and advertising content for businesses based on a website. The focus is on defining the “Business DNA,” consisting of Brand Aesthetic, Brand Tone of Voice, Business Overview, Brand Values, and Tagline. The creator demonstrates how to create these values with the help of AI tools like Gemini or ChatGPT by using template screenshots and having AI fill them in. Next, it shows how to set logos, colors, and fonts, and create campaigns showcasing the product in various contexts. The creation of videos and photo shoots is also explained, with AI generating various variations that can be customized and downloaded. The tool is particularly useful for ideation and creating marketing materials.

  The video explicitly addresses Google’s Meli and uses Gemini and ChatGPT as supporting AI tools. It is better suited for intermediate users who already have basic knowledge of marketing and branding.

• AI Helped Spark a Quantum Breakthrough. "The World 'Is Not Prepared'
  4.5.2026, 21:22:09

  The video discusses recent advances in quantum computing research accelerated by AI and the potential threats to modern internet security. Three main factors are highlighted: improvements in quantum computers, more efficient algorithms, and AI-driven discovery of these algorithms. This combination could significantly reduce the size of quantum computers needed to break modern encryption.

  Google has published research findings showing that a future quantum computer with fewer than 1,200 logical qubits could attack certain encryption methods. Additionally, researchers from Caltech and Oatomic have argued that Shor’s algorithm could run on just 10,000 reconfigurable atomic qubits at cryptographically relevant scales. AI played a crucial role in developing these algorithms by searching through thousands of possibilities and improving algorithm efficiency.

  Companies like Cloudflare are responding to these developments by advancing their targets for transitioning to quantum-safe security. Cloudflare aims to be fully quantum-safe by 2029, including authentication. The shift to quantum-safe cryptography is complex, however, and requires updating multiple systems and rotating secrets.

  Concluding remarks: The video addresses OpenAI and open-source tools like Open Evolve and is aimed at intermediate and advanced viewers.

• Google's New AI Update Just Shocked The AI Industry – Gemini 3.5 Pro , Gemini Omni, Gemini Spark
  20.5.2026, 11:17:24

  The video presents Google’s latest AI features and products, primarily based on the Gemini ecosystem. Here are the key points:

  1. **Gemini Omni**: A new model capable of processing text, images, videos, and audio to create and edit multimodal content. It enables video creation and editing through natural language commands. For example, it can create explanatory videos on complex topics like protein folding or edit existing videos retroactively.

  2. **Gemini 3.5 Flash**: A new Gemini family model specifically optimized for coding. It’s faster and more powerful than previous versions and is particularly suited for agent-based coding tasks.

  3. **Anti-Gravity 2.0**: A revised version of Google’s agent-based development platform. It enables the creation of complex projects, such as an operating system, through collaboration of multiple sub-agents. The platform is now available as a standalone desktop application and offers a variety of integrations and features.

  4. **Gemini Spark**: A personal AI agent that runs continuously in the background and completes tasks on behalf of the user. It can write emails, manage appointments, and even handle complex projects like planning a block party. Spark can interact with various tools and sync tasks across multiple devices.

  5. **Docs Live**: A new feature allowing users to create and edit documents with their voice. This makes it easier to quickly capture ideas and information without manual typing.

  6. **Revamped Gemini App**: The Gemini app has been completely redesigned, offering a more intuitive user interface with enhanced content creation and editing features. New features include Gemini Omni integration for video editing and the “Daily Brief” agent, which provides users with a personalized overview of their tasks and appointments.

  7. **Google AI Pix**: A new app for image editing that allows users to precisely edit and create images. It offers features like removing or altering objects in images and translating text.

  8. **Stitch**: A design tool enabling users to quickly and easily create user interfaces and websites. It offers features like creating UI designs through voice commands and integration with other tools.

  9. **Google Flow**: A platform for creative projects now offering new features like simultaneously executing multiple commands and creating custom tools. Google Flow Music enables music creation through voice commands.

  The video explicitly addresses Google’s own models and tools such as Gemini Omni, Gemini 3.5 Flash, Anti-Gravity 2.0, Gemini Spark, Docs Live, Google AI Pix, Stitch, and Google Flow. It is better suited for intermediate users already familiar with AI tools who want to expand their application possibilities.

Theo – t3․gg (10 new videos)

• I’m scared to make this video
  20.5.2026, 03:51:05

  The YouTuber expresses strong criticism of Google, particularly regarding the latest developments around the Gemini 3.5 Flash model, the Anti-Gravity CLI, and the treatment of customers like Railway. He begins with a warning that his criticism could jeopardize his career, as Google has previously demonetized videos and restricted his reach. Despite these risks, he wants to expose the problems he sees with Google’s current products and decisions.

  The main points of criticism include:
  1. **Gemini 3.5 Flash Model**: Although the model performs well in some benchmarks, it is extremely inefficient in token usage, making it very expensive. The YouTuber provides examples where the model fails to execute tasks correctly, such as rewriting a simple game that works flawlessly with other models like GPT-55.
  2. **Anti-Gravity CLI**: The successor to the open Gemini CLI is, according to the YouTuber, heavily buggy and user-unfriendly. Additionally, Google has discontinued support for the open Gemini CLI and replaced it with the closed Anti-Gravity CLI, disappointing the community.
  3. **Customer Treatment**: Google suspended the account of Railway, a customer spending over 2 million dollars monthly, without providing reasons, causing massive outages. The YouTuber mentions similar incidents in the past that demonstrate Google Cloud’s unreliability.

  The YouTuber emphasizes that despite its resources and talent, Google fails to produce good products due to internal politics and lack of collaboration. He stands behind former Google employees who tried to create meaningful solutions and criticizes the decision to end their work in favor of a closed, buggy product.

  The YouTuber specifically addresses Google’s Gemini 3.5 Flash, Anti-Gravity CLI, and Google Cloud. The video is aimed at intermediate or advanced viewers, as it covers technical details and benchmarks.

• Spending $40,000 in Copilot for $40
  19.5.2026, 02:25:55

  The video discusses the recent changes to GitHub Copilot’s billing model, which shifted from a fixed message limit to a token-based billing system. The author, who uses a free Copilot Plus license himself, demonstrates how to exploit the old system to incur substantial inference costs. He shows how by strategically using Copilot with complex cryptography puzzles and agentic workflows, he drives up costs for Microsoft. The author argues that the billing model change was necessary because the old system was no longer sustainable and Microsoft didn’t have enough computing power to meet demand. He emphasizes that this is not a “rug pull” but a necessary adjustment to continue operating the program.

  Conclusion: The video specifically addresses GitHub Copilot, Claude Code, Codex, Cursor, OpenAI, and Anthropic. It is aimed at intermediate and advanced users.

• AI Is Hacking Everything Now…
  15.5.2026, 20:09:07

  The video discusses a series of serious security vulnerabilities and exploits in various software and operating systems, particularly Linux. Several critical security issues are highlighted, including “Copy Fail,” “Dirty Frag,” and an attack on 84 Tanstack npm packages. The speaker emphasizes that the speed and frequency of these exploits is alarming and that traditional security practices, such as the 90-day disclosure period, are no longer sufficient. He argues that the use of AI has accelerated and simplified the discovery and exploitation of security vulnerabilities, ushering in a new era of software security.

  The speaker proposes that the industry must make drastic changes to address these new challenges. This includes introducing a new tier of trusted actors who are informed about security vulnerabilities early on, as well as a fundamental shift in open-source culture to control and delay code disclosure. He also emphasizes the need to build software more securely from the ground up, for example by using safer programming languages like Rust and developing better architectures.

  The speaker also shares personal measures he is taking to protect himself from these threats, such as regularly creating backups and educating his family about security risks. He concludes with the hope that his warnings are taken seriously and that the industry works together to find solutions to address the growing security challenges.

  AI Tools/Models/Providers: Claude, OpenAI, Gemini, Open-Source (Linux, npm packages, Tanstack), Mythos, OpenAI Daybreak, GPT-4.7, Claude Opus 4.7, Gemini 31 Pro, GPT-5.5

  Target Audience: Intermediate to Advanced.

• I’m done.
  14.5.2026, 10:08:59

  The video addresses Anthropic’s announcement that starting June 15, paid Claude plans will receive dedicated monthly credits for programmatic usage. These credits cover the use of the Agent SDK, Claude-P, and third-party apps based on the Agent SDK. The speaker is disappointed because this change severely restricts Claude usage in third-party tools like T3 Code, OpenClaude, and others, reducing usage limits by 25 to 40 times. He criticizes Anthropic for failing to provide clear communication despite months of requests, and now presenting a solution that seems more like a restriction than an improvement. The speaker emphasizes that this is an attack on open-source projects and that Anthropic is severely limiting open and programmatic usage. He announces that T3 Code will introduce an option to choose between the improved user interface and the original, but limited usage. He advises viewers to use alternative solutions like Codex and expresses his disappointment with Anthropic’s behavior.

  **AI Tools/Models/Providers:** Claude (Anthropic), OpenAI, Codex, OpenClaude, T3 Code, Agent SDK, Claude-P, Open Source
  **Target Audience:** Intermediate to Advanced

• Stop letting your agents write Markdown.
  13.5.2026, 06:46:31

  The video discusses the pros and cons of Markdown compared to HTML, particularly in the context of usage by AI agents. The author argues that while Markdown is simple and portable, it is often too restrictive and should be replaced by HTML, which enables richer and more interactive content. He references articles by Thoric and Andrej Karpathy that share similar views, and provides examples of how HTML can be used for various tasks like planning, code reviews, and designs. The author emphasizes that HTML offers higher information density, is easier to read and share, and enables interactive elements. He concludes with the thesis that the future of human-machine interaction could lie in interactive videos and simulations, and encourages viewers to use HTML as a starting point and explore further.

  The video specifically addresses Claude Code, Anthropic, OpenAI, and specific tools like Copilot Kit. It is aimed at intermediate to advanced users interested in engaging with AI agents and their output formats.

• I wish this was clickbait
  12.5.2026, 10:52:14

  The video discusses the future of Bun, a JavaScript toolkit originally written in the Zig programming language. The speaker, a long-time Bun supporter, expresses concerns about Bun’s stability and future, particularly on Windows, and mentions that some developers like Dax from Open Code have switched to Node.js due to these issues. A central topic is Bun Team’s decision to rewrite Bun in Rust to address stability issues and improve maintainability. The speaker highlights that while this reimplementation is promising, it also brings new challenges, particularly due to extensive use of “unsafe” code in Rust, which points to potential security and stability risks. He also discusses Bun’s integration into Claude Code, an Anthropic tool, and the potential impact of Claude Code’s current problems on Bun’s development. The speaker concludes with hope that the Rust reimplementation of Bun will succeed, though he remains skeptical about short-term benefits.

  The video specifically addresses the AI models and tools Claude and Mythos and is aimed at intermediate to advanced users.

• We all fell for it…
  11.5.2026, 06:45:20

  The video discusses the impact of AI code tools on developer skills and working methods. The speaker shares his personal experiences and reflects on the pros and cons of these tools, particularly regarding productivity, cognitive atrophy, and dependence on AI.

  Key points of the video:

  1. **Productivity Gains**: AI code tools enable developers to work faster and more efficiently by automating repetitive tasks and solving complex problems.

  2. **Cognitive Atrophy**: Excessive use of AI tools can cause developers to lose their skills as they engage less with code details. This is referred to as “cognitive debt.”

  3. **Dependence and Vendor Lock-in**: Developers can become dependent on specific AI tools, which can cause problems if these tools become unavailable or costs increase.

  4. **Quality of Work**: AI tools can improve code quality by reducing errors and suggesting better solutions. However, they can also lead to superficiality if developers don’t fully understand the suggested solutions.

  5. **Working Method**: The speaker emphasizes the importance of using AI tools as aids to improve one’s own work rather than relying entirely on them. He suggests using AI tools for planning, brainstorming, and research while handling implementation yourself.

  6. **Vendor Lock-in and Reliability**: The speaker argues that developers should not be dependent on a single AI tool. He recommends using various tools and providers to increase reliability and flexibility.

  7. **Long-term Impact**: The speaker warns that excessive use of AI tools can negatively affect developers’ careers in the long run if they don’t continue developing their skills.

  The video specifically addresses AI tools and models like Claude, OpenAI, Gemini, and specific tools like Cursor, Browserbase, and T3 Code. It is aimed at intermediate and advanced developers interested in understanding the impact of AI on their work.

• Anthropic just…wait what
  7.5.2026, 09:08:36

  The video discusses the current partnership between Anthropic and SpaceX (or Elon Musk’s XAI) and the associated strategic implications for the AI industry. Anthropic, a leading AI provider, faces a massive compute problem as demand for its models, particularly Claude, far exceeds available computing resources. This scarcity has led to restrictions on usage limits and price adjustments, which, however, are not primarily aimed at profit maximization but rather at using limited compute resources more efficiently. The partnership with SpaceX, which has substantial compute capabilities, is intended to fill this gap. At the same time, the strategic importance of Cursor, an AI-powered coding tool with valuable data essential for AI model training, is highlighted. The analysis shows that both Anthropic and XAI are attempting to address their respective weaknesses (compute and data, respectively) through this cooperation, while OpenAI remains as the main competitor in the background. The video analysis is detailed and suitable for intermediate to advanced users, as it provides deep insights into the strategic decisions and technical infrastructure of the AI industry. Anthropic, SpaceX/XAI, Cursor, OpenAI, and specific compute infrastructures like Nvidia GPUs and various cloud providers are explicitly addressed.

• Get In, We’re Leaving GitHub
  6.5.2026, 19:43:52

  The video discusses current challenges and alternatives to GitHub, particularly in light of GitHub’s increasing reliability problems such as random merge reversions and lengthy outages. The author emphasizes the need to explore alternatives and evaluates various options like GitLab, Bitbucket, GitTea, Forgejo (Codeberg), and new approaches like Pierre, Graphite, and Entire.

  **Main Points:**

  1. **GitLab**:
  – Often mentioned as an alternative, but has significant UX problems and is less user-friendly than GitHub.
  – The codebase is large and complex, making maintenance and improvements difficult.
  – GitLab is more of an enterprise solution focused on CI/CD and integration, but not necessarily an improvement over GitHub.

  2. **Bitbucket**:
  – Primarily marketed as a cost-effective alternative for businesses already using Atlassian tools.
  – Integrations with Jira and other Atlassian products are strong, but user experience and functionality are not comparable to GitHub.

  3. **Forgejo (Codeberg)**:
  – An open-source alternative that emerged from a fork of GitTea.
  – Offers a simple, self-hosted solution with good performance and transparency.
  – The author is impressed by the user-friendliness and community behind Forgejo and even donates to the project.

  4. **Pierre**:
  – A new approach that lays the groundwork for a next generation of Git hosting solutions.
  – Focus on high throughput capability and integration of agents that generate large amounts of code.
  – Pierre has already achieved impressive performance metrics and could form the basis for future GitHub alternatives.

  5. **Graphite**:
  – Provides improved code review workflows and was recently acquired by Cursor.
  – Potential to create an entirely new type of developer platform that goes beyond traditional GitHub features.

  6. **Entire**:
  – Founded by former GitHub CEO Thomas Dohmke.
  – Develops tools to track and improve agent context when generating code.
  – Investing in the future of development, particularly in connection with AI agents.

  **Conclusion**:
  The video specifically addresses open-source tools like Forgejo (Codeberg), Pierre, and specific companies like Graphite and Entire. It is aimed at intermediate and advanced users interested in engaging with the technical details and strategic considerations of Git hosting solutions.

• Prime is (mostly) right about AI
  5.5.2026, 08:53:45

  The video discusses the changing economics of the AI industry, particularly regarding the usage of AI models like Claude and GitHub Copilot. The speaker responds to a video by Primagen that analyzes current changes in AI economics.

  The speaker emphasizes that recent pricing model changes from Anthropic and Microsoft are not aimed at extracting more money from end users but rather at managing limited compute capacity (GPUs). For example, Anthropic attempted to restrict Claude Code usage in cheaper tiers to preserve computing resources for enterprise customers. Microsoft also adjusted its pricing models for GitHub Copilot, which the speaker attributes to limited availability of computing power.

  Another important point is the efficiency improvements of AI models. Despite higher token costs per query, newer models like GPT-55 are more efficient and cheaper to use, especially in mid-range and low-tier settings. The speaker argues that costs for genuine work tasks are declining when considering model efficiency.

  The speaker also criticizes the assumption that Google is less subsidized. He argues that Google has actually been very aggressive in subsidizing but, due to the poor quality of its models and rapid adjustments to usage terms to avoid overload, the effects are less visible.

  Overall, the speaker agrees with Primagen’s analysis that AI industry economics are changing, but emphasizes that the main cause is limited compute capacity rather than corporate greed.

  **AI Tools/Models/Providers:** Claude (Anthropic), GitHub Copilot (Microsoft), GPT-55 (OpenAI), Google (Gemini)
  **Target Audience:** Intermediate

Liam Ottley (2 new videos)

• Claude Managed Agents Will Make Millionaires (do this now)
  20.5.2026, 02:09:16

  The video discusses the significance and applications of Claude Code Managed Agents, a new Claude technology that is promoted as a powerful tool for business applications. The speaker, Liam Ottley, emphasizes that these agents enable creating a kind of artificial intelligence for enterprises that functions as a central work environment and enables continuous learning. He explains that these agents can be hosted in the cloud and you only pay for actual runtime, making them cost-effective. By connecting to databases, documents, and custom tools, these agents can act as long-term, learning-capable assistants that update themselves overnight and manage their memories. Liam Ottley compares this to human cognitive architecture and emphasizes how this technology can help enterprises work more efficiently and solve problems. He also mentions OpenAI and its competing products, highlighting the advantages of Claude Code Managed Agents. The speaker encourages viewers to engage with this technology and explore its applications, particularly regarding the creation of products or services for customers.

  The video explicitly covers Claude Code Managed Agents and OpenAI and is geared toward intermediate and advanced users.

• How to Make $20,000/Month with Claude Code
  23.4.2026, 20:10:59

  The video discusses the future of AI agencies, particularly regarding the introduction of retainer models starting in 2026. The speaker argues that tools like Claude Code have significantly reduced the costs and effort for developing automations and agents, making it attractive for agencies to switch to a retainer model. Small and medium-sized businesses (SMBs) in particular benefit since they need fast and cost-effective solutions. The speaker compares this to Designjoy’s model, where customers pay monthly fees for design services. He emphasizes that the technology is now mature enough to make such retainer models profitable and valuable for both parties. An example is Tyler, who offers AIOS installations and Claude Code setups for business clients while charging monthly fees of $2,500. The speaker sees great potential in automating audits and development processes, which significantly reduces the time to value for customers. He suggests that agencies should specialize in managing and optimizing automations, as this will be the most valuable part of their services in the future. Overall, he views the current time as the most exciting phase for AI agencies, particularly through the use of Claude Code.

  The video explicitly covers Claude Code and is geared toward intermediate or advanced users.

Productive Dude (5 new videos)

• Automate ANYTHING with Claude! (Here's how…)
  29.4.2026, 13:01:22

  The video demonstrates how to automate your business with Claude at three different levels: from basic usage of Claude in chat to integrating Claude into a custom platform. The three levels are:

  1. **Level 1: Basic chat capabilities**
  – A Skill is created in Claude by building a folder structure with a `skill.md` file, reference files, and examples.
  – The Skill is uploaded and used in Claude to automate tasks like qualifying leads and drafting emails.
  – Example: A lead qualifier Skill that rates leads and creates email drafts.

  2. **Level 2: Routines with Skills and Connectors**
  – Skills are stored in a GitHub repository and used in Routines that are triggered on a schedule or by events.
  – Example: A Routine that qualifies all leads from the previous week every Monday at 8 AM and creates email drafts.
  – Integration with tools like Google Drive and Gmail to read leads and create email drafts.

  3. **Level 3: Custom Platform**
  – Building your own CRM platform that communicates directly with Claude.
  – Using a Model Context Protocol (MCP) Server or direct API calls to qualify leads and create emails.
  – Example: A custom CRM platform that reads leads from a form, qualifies them, and creates emails.

  The video walks through how to implement these levels step by step, from creating a simple Skill to integrating it into a custom platform.

  Final note: The video explicitly features Claude and is aimed at intermediate to advanced users.

• ChatGPT 5.5 "Spud" just dropped… did it destroy Opus 4.7?
  24.4.2026, 12:01:55

  The video provides a detailed analysis and first impressions of GPT 5.5, which was released on April 23, 2026. The creator compares the model to other AI models, particularly Claude models from Anthropic, and highlights the strengths and weaknesses of GPT 5.5. Key points include the model’s improved ability to complete tasks independently without constant oversight, as well as its strengths in areas such as code writing and debugging, online research, data analysis, document creation, and software operation. The creator tests GPT 5.5 live in Codeex and shows how the model can handle multiple complex tasks simultaneously, including creating a dungeon game, a landing page, and an artificial life simulation. Benchmarks show that GPT 5.5 performs well in areas like long context, terminal work, and complex reasoning tasks, while Claude 4.7 excels in software development and agent-based tasks. The creator concludes that GPT 5.5 is particularly suitable for long-context tasks, terminal work, and challenging reasoning problems, while Claude 4.7 is better for daily software development and agent-based tasks.

  Final note: The video explicitly features GPT 5.5 from OpenAI and Claude 4.7 from Anthropic and is aimed at intermediate to advanced users.

• Claude Live Artifacts just dropped… ALL your tools in one place!
  23.4.2026, 13:00:18

  The video shows how to create a CRM system using Claude’s new Live Artifacts feature that aggregates data from various sources like Notion, HubSpot, Google Sheets, and Gmail and displays it in a unified dashboard. The process begins by connecting your desired apps through the Connector function in Claude. You then create a Live Artifact through targeted prompts that fetches and displays data in real time. The user demonstrates creating a CRM dashboard with filters for different lead categories and an integrated email function controlled via Gmail. After some adjustments and troubleshooting, the finished dashboard displays all leads from Notion and allows you to draft emails to contacts directly. The video emphasizes the versatility and efficiency of the Live Artifacts feature for data aggregation and analysis.

  The video explicitly features Claude and is aimed at intermediate to advanced users.

• ChatGPT Images 2.0 just dropped… text, transparency and more! 🤯
  21.4.2026, 22:40:54

  The video introduces the latest version of OpenAI’s image model, Image V2, and evaluates its capabilities and limitations. The creator highlights that the model is capable of following detailed instructions, placing objects precisely, and rendering dense text, though with some limitations in text consistency. A special feature is the “Thinking” function, which enables the model to analyze and optimize prompts, leading to better results. The model shows strengths in creating UIs, magazine collages, handwritten essays, and photorealistic images. It supports various aspect ratios and is available in multiple languages. The creator tests the model with various tasks, such as creating website mockups, redesigning YouTube thumbnails, and generating images with transparent backgrounds. The model proves capable of delivering impressive results but also has some weaknesses, particularly in rendering text and precisely implementing instructions. Finally, the creator attempts to create a thumbnail for the current video using Image V2 to demonstrate the practical applicability of the model.

  The video explicitly features OpenAI’s Image V2 and is aimed at intermediate users who already have experience with AI tools.

• Claude + Higgsfield: Build Beautiful ANIMATED Websites! (Claude Tutorial)
  21.4.2026, 13:00:45

  The video demonstrates how to quickly create and deploy an animated website using AI tools like Higgs Field and Claude Design. The process starts by creating images and videos in Higgs Field, converting an image into a video with an animated scene. The video is then converted to WebM format and uploaded to Claude Design, where a landing page is created with the video and additional elements like text and cards. The finished website can then be deployed via Netlify, with the entire process completed in less than 5 minutes. The creator emphasizes the simplicity and speed of the procedure and suggests using such websites as an outreach method to acquire potential customers.

  Final note: The video explicitly features Higgs Field, Claude Design, Claude Code, and Netlify and is aimed at intermediate to advanced users.

Nick Saraev (3 new videos)

• How to Build Mobile Apps with Claude Code: Full Course (2026)
  11.5.2026, 17:51:20

  **AI Tools/Providers covered:** Claude, OpenAI, Gemini, Open-Source, specific tools such as Cursor, Lovable, Cline, n8n

  **Target audience:** Intermediate

• How to Use Claude Code for FREE (2026)
  2.5.2026, 01:02:11

  The video shows how to use Claude Code for free by using an open-source alternative called “Free Claude Code”. This alternative enables the use of the same Claude Code interface, but with cheaper backend models that offer approximately 80-90% of the quality of Opus 4.7 at 2-5% of the cost. The creator demonstrates the setup and use of this alternative by building a simple habit-tracking app. Various models and platforms such as Open Router, NVIDIA NIM, and Ollama are introduced, which can serve as backends for the free Claude Code alternative. The creator also shows how to set up and use these models, as well as how to optimize quality and costs by combining different models. The video is aimed at intermediate users who already have experience with Claude Code and are looking for a cost-effective alternative. Specific tools and models such as DeepSeek V4 Flash, GLM 4.7, and Gemma 4 are covered.

• I Built a $1M/y SaaS with Claude Code, Here's How
  20.5.2026, 13:30:22

  The video describes the process of developing and monetizing an AI-powered power dialer called Clarvo, built with Claude Code. The speaker shares his experiences and lessons learned on how they achieved one million dollars ARR (Annual Recurring Revenue) with Clarvo.

  First, the product Clarvo is introduced, an AI-powered power dialer that helps companies make more calls per unit of time and increase the number of successful connections. This is particularly useful in industries that rely heavily on phone acquisition, such as HVAC, plumbing, and roofing.

  The speaker explains how they worked with Claude Code to find various solutions to improve the call connection rate. They started by defining the problem and asked Claude Code to enumerate all possible solutions. They then filtered out the feasible ideas and implemented them in simulations to find the best solutions. One of the successful approaches was “Predictive Pacing”, where multiple calls are made simultaneously to increase efficiency.

  Another important point is pricing. The speaker emphasizes that they gradually increased the price until it became difficult to find customers. They started at $100 per month and increased the price to $250 per month, which proved successful.

  The speaker also warns against using too many frameworks and tools, as they often cause more problems than they solve. Instead, he recommends focusing on the fundamental capabilities of the model and minimizing complexity.

  Finally, the speaker emphasizes the importance of choosing problems that are truly valuable to customers and for which they are willing to pay. He advises focusing on industries that have large budgets and where solving the problem provides significant added value.

  The video explicitly covers Claude (Claude Code) and is more suitable for intermediate or advanced users who already have experience developing SaaS products.

Leon van Zyl (10 new videos)

• Claude Code Builds Portfolio Websites That Look Like This
  19.5.2026, 14:00:24

  In this video, Leon demonstrates how to design a personal portfolio website that looks and functions like a Coding Agent CLI (similar to Claude Code). The process begins with creating a new Next.js project and installing skills like “next best practices” and “front end design”. Leon uses Claude Code to build the website by employing specific prompts that generate a terminal-like user interface and animated responses. The website can be connected to a knowledge database, allowing visitors to ask questions and receive answers. Leon also shows how to deploy the website on a hosting platform and automatically update it when code changes are made.

  The video explicitly covers Claude Code and Next.js and is better suited for intermediate users who already have basic web development knowledge.

• Claude Code Agent View: Parallel Agents Are Here
  14.5.2026, 10:51:58

  The video reports on a complex supply chain attack targeting open-source packages in the npm ecosystem, affecting over 100 packages with over 50 million weekly downloads. The attack exploited a vulnerability in Tanstack’s release process by having an attacker create a pull request in a fork of the repository, which triggered the CI/CD workflow. By using the “pull request target” option, the attacker was able to inject malicious files into the CI server’s shared cache, which later stole a valid npm publish token and published compromised package versions. The malware spread further by hunting for additional npm publish tokens and infecting more packages, including those from Mistral AI, UiPath, and Open Search. The malware deeply integrated into developer environments and even employed a “dead man switch” that would delete the root folder of the infected system upon detection.

  To defend against such attacks, the video recommends using PNPM 1 or higher, which offers features like “minimum release age”, “block exotic subdependencies”, and “approved builds” to prevent installation of malicious packages. Additionally, Sentry is presented as a tool for debugging production issues, working with an AI-powered agency called Seir to automatically investigate and resolve problems.

  The video addresses specific tools like PNPM, Sentry, and Seir Agent and is intended for intermediate to advanced users.

• Codex CLI Full Tutorial: Build Your First AI Image Generator from Scratch
  11.5.2026, 11:17:21

  This video demonstrates step-by-step how to build an AI image studio for creating YouTube thumbnails, posters, banners, and other graphic content. The process starts with setting up a Next.js project using the Codex CLI tool, which is based on GPT-5.5 and a high reasoning level. A database is set up with Docker and Postgres, and necessary tables for user authentication are migrated.

  The focus is on designing a user-friendly interface that enables users to upload reference images, write prompts, and generate images. The developer uses the capabilities of the Codex tool to design and test the user interface while adhering to a predefined design system. After designing the interface, the actual functionality is implemented using the OpenAI API key for the GPT-4 image model. The developer shows how to upload reference images and assets and how to generate thumbnails that combine these elements.

  Finally, the user interface is adjusted to ensure image generation occurs only through the dashboard and not from the landing page. The landing page is redesigned with a generated image and marketing copy. The video emphasizes the efficiency and time savings provided by using Codex and OpenAI, while noting the token limitations of the ChatGPT Plus plan.

  The video explicitly covers OpenAI (GPT-5.5, GPT-4 Image Model) and Codex. It is intended for intermediate and advanced users as it covers advanced concepts such as Docker, Postgres, Next.js, and API integration.

• Create Custom OpenCode Agents #Shorts #OpenCode #AICoding
  10.5.2026, 07:00:16

  The video shows how to create custom agents in OpenCode. By default, there are two agents: “build” and “plan”. To create your own agent, you run the command `open code agent create` in the terminal. Next, you enter a description of the agent, such as an agent named John that only responds with emojis. After creation, you can use the spacebar to define which functions or tools the agent can access. You also select the agent mode: either for primary and subordinate roles or only as a subordinate agent. The video demonstrates the creation of a subordinate agent named John and shows how the main agent delegates a task to John. You can track the subordinate agent’s work and view its reasoning and outputs. Finally, the video emphasizes that this is just a demonstration, and in practice, you could use more specific system prompts and tool access for subordinate agents.

  The video covers OpenCode and is suitable for intermediate users.

• OpenCode’s Best Hidden Feature #Shorts #OpenCode #AICoding
  9.5.2026, 07:00:19

  The video explains how to set different models for different modes in OpenCode. For example, you can use a powerful model like GPT-5 for planning mode and a fast, cost-effective model like Big Pickle for implementation mode (Bold Mode). Alternatively, you can use GPT-5.5 for planning but reduce effort by selecting the “/variants” command with the “low effort” option. This allows planning to be created by an intelligent model while implementation can be handled by a less powerful but faster model.

  The video covers OpenCode models and is better suited for intermediate users.

• I Turned Hermes Agent Into a Coding Agent
  8.5.2026, 11:02:33

  The video demonstrates how to use the Hermes Agent as a coding agent to build and deploy a web app online. The process involves setting up the Hermes Agent on a VPS, integrating it with Telegram for communication, installing the Vercel CLI tool for deployment, and configuring the necessary skills for the agent. The creator tests whether the agent can create a personal portfolio page by scraping information from the creator’s YouTube channel and building an attractive frontend design. The agent successfully creates the app, deploys it to Vercel, and provides a public URL that opens the app in a browser. The video also shows that the agent can make changes to the app and deploy them automatically.

  The creator concludes that Hermes is suitable as a coding agent for simple tasks and quick dashboards, but not for complex software projects. The video explicitly covers Hermes Agent, OpenAI Codex, GPT 5.5, Vercel, and Telegram. It is intended for intermediate and advanced users.

• This free OpenCode trick saves thousands #opencode #aitools #hacks
  7.5.2026, 13:38:39

  The video explains how to use free AI models for code generation in OpenCode. First, you run the “connect” command and search for the provider “OpenCode Zen”. Next, you generate an API key through a provided URL, which is free. After entering the API key, you receive a list of supported models, including Big Pickle, HY3, Minimax M2.5, and Neurotron 3 Super from Nvidia. These models are powerful and completely free.

  The video covers OpenCode and OpenCode Zen and is aimed at intermediate users.

• I Built a Coding Agent That Runs Locally for Free
  6.5.2026, 12:25:00

  The video introduces the open-source tool “Honeyfree”, which allows you to autonomously plan and implement software projects. You describe to the tool what you want to build, and it plans the features, adds them to a Kanban board, and implements them automatically. The tool supports various models like Alum Studio and Ollama and can also break down complex tasks into smaller features. The creator demonstrates building a simple to-do app and shows how new features can be added and implemented. The video emphasizes that this is now possible with free models, which was not the case a few months ago. It also explains how to download models like Qwen 3.6 or JML4 and use them in Alum Studio or Llama Studio. The creator recommends increasing the context window length of models to at least 64,000 tokens for better performance. The video also shows how to install and set up Local Forge to create and manage projects. It emphasizes that while free models are good at writing code, they require more detailed instructions for better results. The creator recommends using a paid model like Claude for planning features while using free models for the actual implementation. The video ends with an invitation to sign up for a masterclass course that teaches how to build applications with coding agents.

  The video covers open-source models like Qwen 3.6 and JML4, as well as tools like Alum Studio, Llama Studio, and Local Forge. It is better suited for intermediate and advanced users who already have experience using AI models and developing software.

• OpenCode Tutorial for Beginners: Setup, Agents, Skills & MCP
  5.5.2026, 12:33:17

  This video is a tutorial showing how to create a Next.js application using Open Code, an open-source AI tool. The process starts with installing and setting up Open Code, including connecting it with various AI models and providers, both free and paid. The tutorial demonstrates how to add agent capabilities like frontend design and Next.js skills to improve the quality of generated code. It also shows how to use memory files and design systems to increase the agent’s consistency and efficiency. The tutorial continues with creating an application that allows users to input a rough idea of their app and receive a detailed project plan. The agent uses subagents to perform tasks in parallel and protect the main context. At the end, the application is tested and improved, with the agent completely redesigning the UI and running automated tests. The video is suitable for intermediate and advanced users interested in AI-powered coding tools.

  AI Tools/Models/Providers: Open Code (Open Source), OpenAI, Anthropic, Gemini, OpenRouter, BigPikko, HY3, Minimax, Nvidia, Vercel, Cintra AI.

• I Built a Full App Using Only Cursor AI
  4.5.2026, 11:01:35

  In this video, an AI-powered YouTube summarizer is developed using the Cursor tool. The process begins with creating a user interface that takes a YouTube URL and delivers a summary of the video. The requirements include a brief summary (TLDR), five to eight key points, a “Watch these moments” section with timestamps and descriptions, and the original video link.

  The creator uses Cursor and opts for the Composer 2 model to scaffold the project. He installs Next.js and the Shad cn library for the user interface. With the help of Cursor’s agents, a basic user interface is created that meets the requirements. Next, functionality is added to retrieve the transcript of a YouTube video using the YouTube Transcript API.

  For the AI-powered summary, the AI SDK from Cursor is used to return structured data. The creator opts for the “anthropic/claude-2” model from OpenRouter and integrates the API key into an .env file. The agent then generates the summary, including the TLDR, key points, and recommended moments from the transcript.

  The video explicitly covers the tools Cursor, Composer 2, Next.js, Shad cn, YouTube Transcript API, AI SDK, and OpenRouter. It is better suited for intermediate and advanced users.

Tim Carambat (7 new videos)

• Llama.cpp Just Merged MTP And You Should Be Using It.
  18.5.2026, 17:45:34

  The video covers the introduction of Multi-Token Prediction (MTP) in Llama CPP, a popular tool for running AI models locally. MTP enables up to 25% faster token processing without quality loss by predicting multiple tokens simultaneously. The presenter, Timothy Carbat, explains how MTP works and compares it to speculative decoding (SSD), which requires two models, while MTP uses only one. He demonstrates how to enable MTP in Llama CPP and which models support it, including Deepseek V3 and V4, Neotron 3, Quinn 3.5 and 3.6, and Gemma 4. Carbat demonstrates the performance improvement using a benchmark with the Quinn 3.59B model and emphasizes the importance of adjusting the parameter for the number of predicted tokens (n_max). He concludes by noting that such software improvements make local AI usage more efficient and sustainable.

  The video explicitly covers Llama CPP, Deepseek, Neotron, Quinn, and Gemma 4 and is aimed at intermediate and advanced users.

• A New AI Model Just Dropped With A CRAZY Claim.
  5.5.2026, 19:02:32

  The video discusses the announcement of a new model called SubQ from Sub Quadratic, which advertises a 12-million-token context window and allegedly 52 times higher efficiency compared to existing models. The creator, Timothy Karen, expresses skepticism due to missing technical reports and unclear benchmarks. He explains the underlying technology, which is based on “sparse attention,” and compares it with conventional and Flash Attention mechanisms. The benchmarks show that the model performs well in certain tests like SWEBench verified and MRCRV2, but it’s unclear whether these results apply to the 12-million-token model or a 1-million-token preview. Timothy Karen has applied for early access and will share the results in a future video.

  The video explicitly covers the SubQ model from Sub Quadratic and is aimed at intermediate or advanced viewers.

• Hey Anthropic, That Looks Illegal?
  29.4.2026, 21:41:25

  **Summary:**

  Timothy Carbat reports from San Francisco, where he’s attending the AMD AI Dev Day and discussing the use of local models. He criticizes narratives that AI can replace humans, emphasizing that AI is a tool that should be used by people.

  A central theme of the video is the “enshittification” of AI tools, particularly Claude. Anthropic attempted to remove Claude Code from certain subscriptions and later reversed the decision. Additionally, there was a billing problem where users with certain strings in their Git history were incorrectly charged additional fees. This led to negative user reaction as Anthropic initially refused refunds but later offered a solution.

  Carbat argues that such issues indicate that companies like Anthropic are resorting to questionable methods due to cost problems. He recommends using open-source tools like pi.dev or Hermes Agent in combination with local models to avoid such issues.

  **Final Comment:**
  The video explicitly covers Claude from Anthropic and open-source tools like pi.dev and Hermes Agent and is aimed at intermediate users.

• The Cloud AI Situation is Bad.
  28.4.2026, 17:00:17

  The video discusses the “enshittification” of AI tools—the degradation of services and products over time, often accompanied by price increases and feature removal. The author uses examples like Airbnb, Uber, and Netflix to illustrate this phenomenon but focuses mainly on AI-specific examples like GitHub Copilot and Claude Code. With GitHub Copilot, plans were severely restricted, models removed, and terms of service worsened, leading to significant service degradation. Similar issues affect Claude Code, where features were removed and usage limits introduced, negatively impacting user experience. The author argues that these developments indicate that cloud-based AI services are not sustainable long-term and that local AI solutions are the better alternative. Local AI models offer stability since they don’t depend on external factors like price increases or feature removal. Additionally, local models are now powerful enough to handle many tasks previously done in the cloud. The author emphasizes that local AI is the future and that many tasks, particularly productivity and coding-related ones, could soon shift to local machines.

  Final Comment: The video explicitly covers GitHub Copilot, Claude Code, and local AI solutions like Anything LLM. It’s aimed at intermediate and advanced users engaged with the technical and economic aspects of AI.

• DeepSeek V4 Is Here And It Has 1 Million Token Context??
  24.4.2026, 11:00:51

  The video covers the release of DeepSeek V4, a new local language model that includes two variants: DeepSeek V4 Flash (284 billion parameters, 13 billion active parameters) and DeepSeek V4 Pro (1.6 trillion parameters, 49 billion active parameters). Both models support a context window size of one million tokens, enabled by a new technique that reduces KV-cache memory requirements by up to 90%. This technique, based on hybrid attention architecture, could become relevant for smaller models in the future. The models show improved benchmark results compared to earlier DeepSeek versions, particularly at maximum reasoning depth. However, compared to leading cloud models like GPT-5.5 and Opus 4.6, they perform well only in some benchmarks. The technical innovations, particularly the more efficient use of the context window, are highlighted as significant. The video is aimed at intermediate and advanced users interested in local language models and technical innovations.

  **AI Tools/Models/Providers:** DeepSeek V4 (Flash and Pro), TurboQuant, Opus, GPT-5.5, open-source models.

• 27B Beats 397B?! The New Qwen 3.6 Is All About Efficiency
  23.4.2026, 18:15:01

  The video covers the latest version of the Qwen model, Qwen 3.627B, placing it in the context of previous Qwen series models. The author, Timothy Carbat, founder of Anything LLM, focuses on local models and their advantages regarding privacy and cost savings compared to cloud models.

  Qwen 3.627B is described as promising, particularly because of its multimodality and capabilities in the software engineering benchmark (SWE bench). The author compares the model’s performance with earlier Qwen versions as well as cloud models like Claude 4.5 Opus and Gemini. It’s noted that Qwen 3.627B performs well in some benchmarks, though some nuances and potential biases in the benchmark results are also discussed.

  The author emphasizes the importance of transparency when reporting benchmark results and warns against uncritically accepting the results. He speculates that Qwen 3.6 Plus, an API-based version, might be an earlier checkpoint of Qwen 3.627B, given the similarity in benchmark results.

  In summary, Qwen 3.627B is presented as a model worth checking out due to its density of intelligence and multimodality, particularly for users who prefer local models. The author plans to test the model himself and share his experiences with the community.

  The video explicitly covers the Qwen model (open-source) and is aimed at intermediate to advanced users.

• I Just Tried The Brand New Ternary Model And It's Great!
  21.4.2026, 19:38:40

  The video covers the development and significance of one-bit and ternary models in local AI. The speaker, Timothy Carbat, founder of Anything LLM, explains that one-bit models reduce the complexity of conventional LLMs (Large Language Models) by restricting weights to 1 or 0. This enables significant memory reduction, allowing large models like 8B models to run on devices like smartphones or low-end laptops. However, there’s a slight accuracy loss compared to the original 16-bit models.

  Prism ML, a startup with researchers, has developed a practical one-bit model called BitNet that’s actually usable and offers a good balance between accuracy and efficiency. Recently, Prism ML introduced a ternary model that adds an additional “0” to the one-bit system, further improving accuracy while keeping memory requirements significantly lower than conventional models. These ternary models offer nearly the same accuracy as 16-bit models but with a fraction of the resources.

  The speaker demonstrates how to install and run a ternary model on a MacBook M4 Max with 48 GB RAM, explaining the necessary steps and commands. He also shows how to integrate the model into Anything LLM to perform various AI-assisted tasks. Finally, he discusses the future of one-bit and ternary models, speculating whether larger models beyond 8B can be developed with the same efficiency.

  The video explicitly covers one-bit and ternary models, particularly those developed by Prism ML. It’s aimed at intermediate and advanced users interested in the technical implementation and benefits of local AI models.

WorldofAI (10 new videos)

• Gemini 3.5 Flash: Google’s Most Powerful Model Ever! Beats Opus 4.7 & GPT 5.5? (Fully Tested)
  20.5.2026, 06:43:51

  The video discusses the introduction of Google Gemini 3.5 Flash, a new fast and efficient model presented at the Google I/O developer conference. The author has mixed feelings about it since while technically impressive, it also has some drawbacks. The model is faster and more powerful in code editing than previous versions, but it’s also more expensive and consumes more tokens. It’s good for complex tasks like planning and understanding large codebases, but costs can be higher than other models. The author tests the model across various areas like frontend design, SVG generation, and 3D world creation, finding it performs very well in these areas. However, there are also some weaknesses, such as excessive ambition and high token consumption, which can lead to truncation in large projects. Overall, the author considers the model a solid release from Google, especially for users of Google subscriptions. The video is better suited for intermediate and advanced users and explicitly discusses the Google Gemini 3.5 Flash model.

• Google I/O LEAKED! Gemini Desktop App, Veo 4, Qwen 3.7, Composer 2.5, Mythos Soon, & More! AI NEWS
  19.5.2026, 06:45:31

  The video summarizes the week’s major AI news, focusing on Google, Anthropic, Alibaba, Cursor, and others. Google is about to release new Gemini models, including Gemini 3.5 Flash, which should score points with high speed and efficiency. There are leaks about new features like a Gemini desktop app enabling local agent workflows and integration with Google Drive. Additionally, Google might introduce the Veo 4 model, a new video generation model. Anthropic is possibly preparing to launch Claude Mythos, while Alibaba has released Qwen 3.7, a new multimodal model that can compete with top models like GPT 5.5 and Gemini 3.1 Pro. Cursor has released Composer 2.5, which according to tests can keep up with Opus 4.7 while being more cost-efficient. Open Design introduced a new feature for integration with Codex, making UI generation easier. HRM text, an ultra-lightweight model with only 1 billion parameters, shows promising results with minimal training effort. Boston Dynamics presented a video where the humanoid robot Atlas carries and manipulates a refrigerator, demonstrating advances in combining physical control and AI.

  The video explicitly discusses Google (Gemini, Veo 4), Anthropic (Claude Mythos), Alibaba (Qwen 3.7), Cursor (Composer 2.5), open-source tools (Open Design, HRM text), and Boston Dynamics (Atlas). It’s better suited for intermediate and advanced users.

• Hermes Agent Foundation Update: Real-Time Agents, DeepSeek V4 FREE, Native Windows Support, & More!
  18.5.2026, 06:16:23

  The video covers the latest version 0.14.0 of the open-source AI agent Hermes, developed by Nous Research. Key updates include:

  1. **Local Proxy Feature**: Enables using a single subscription (e.g., Claude, ChatGPT, Grok) for various tools and agents without separate API keys.
  2. **Windows Support**: Native Windows support in beta phase, simplifying installation and usage.
  3. **Performance Improvements**: Faster startup times, optimized browser automation, and improved caching mechanisms.
  4. **Video Generation**: New capability for autonomous video creation within workflows.
  5. **Supergrok Integration**: Direct support for Grok’s Supergrok subscription, including access to Grok 4.3, text-to-speech, image and video generation, plus X-Search.
  6. **Handoff System**: Enables seamless switching between models or personas without losing context.
  7. **Additional Improvements**: Integrated X-Search, Vision Model Support, Discord history backup, LSP semantic diagnostics, and more.

  The video is better suited for intermediate to advanced users and explicitly discusses open-source tools like Hermes Agent, N8N, and Grok.

• Stop Paying $200/Month for Claude Code! Here’s a FREE Option!
  17.5.2026, 05:59:20

  The video introduces Mistral Vibe, an open-source and partially free tool for AI-powered development, positioned as an alternative to Claude Code and Cloud Code. Mistral Vibe is a terminal-based AI coding agent that can write, test, refactor, and even deploy code. It supports asynchronous tasks, integrates with tools like GitHub, Jira, and Slack, and offers customizable agent workflows for automating long-term tasks. Particularly highlighted are the capabilities for documenting shell aliases, creating sub-agents for specific tasks like PR reviews and test generation, and using slash commands for repeated tasks. The tool is free and open-source, with the option to use your own API keys. For intensive use, there are paid plans like Lay Chat Pro ($14.99/month) and Late Chat Team ($24.99/seat/month), with students receiving 50% discount. Installation is straightforward via bash or Python method, with additional integrations for VS Code and JetBrains IDEs.

  The video demonstrates the installation and basic usage of Mistral Vibe, including creating a frontend landing page and generating tests for a codebase. It emphasizes that Mistral Vibe enables efficient automation through asynchronous agents and parallel execution. The conclusion recommends Mistral Vibe as a cost-effective and powerful alternative to existing tools, especially for developers seeking terminal-based automation.

  **Final Comment:** The video explicitly discusses Mistral Vibe (open-source) and is better suited for intermediate and advanced users.

• Gemini 3.5 Flash + Pro: Powerful, Cheap, & Fast NEW AI Model! (Fully Tested)
  16.5.2026, 06:11:06

  The video discusses the latest developments and leaks regarding Google’s Gemini models, particularly the checkpoints for Gemini 3.5, which are set to be unveiled soon at the Google I/O conference. Initially, the Gemini 3.2 variants (Fanta, Sprite, Cola) and the Pro version were presented, which were good but not revolutionary. However, the latest checkpoints, internally called “Cappuccino,” show impressive progress. Particularly noteworthy is the model’s ability to generate complex applications like a Minecraft clone or a Mac OS clone, with detailed and consistent outputs. The Gemini 3.5 Flash variant shows strong improvements in code generation, aesthetic design, and spatial consistency, but sometimes remains too repetitive and cluttered in UI generation. There are also hints of a secret testing phase for the Gemini 3.1 Pro variant, which also delivers promising results.

  The video explicitly discusses Google’s Gemini models and is better suited for intermediate to advanced users interested in the latest developments in AI technology.

• Codex + Ollama = Free Unlimited Coding AI
  15.5.2026, 06:48:19

  The video explains the integration of Ollama into OpenAI’s Codex, which enables using open-source models locally on your own computer. Codex is an AI coding agent that helps with developing, editing, reviewing, and deploying software. Ollama allows running open-source models like Deepseek, Gemma 4, or Qwen 3.6 locally. The combination of both tools enables using these models for free in Codex. The video shows step-by-step how to install Ollama, host a model like Gemma 4 locally, and connect it with Codex. It demonstrates how to accomplish tasks in Codex using the locally hosted model, e.g., creating a landing page. It also explains how to switch back to the original Codex experience.

  The video explicitly discusses OpenAI’s Codex and Ollama and is better suited for intermediate users.

• Anthropic’s Downfall? GPT-5.6, Gemini 3.2, Robots Running A Full 8-hr Shift, & Qwen 3.6 Plus FREE!
  14.5.2026, 06:39:49

  The video covers current developments in AI technologies, particularly from Google, OpenAI, and Anthropic.

  Google is intensively testing new variants of Gemini 3.2, including Flash and Pro versions, which have delivered rather disappointing results so far. Front-end generation shows weakness compared to earlier versions, and expectations for the new models have not been met. Additionally, an unreleased multimodal video model from Google was leaked, showing promising but still early results.

  OpenAI is intensively working on GPT 5.6, with internal tests and potential releases in June. There are indications of improved security reviews and possible new variants like Ember Alpha and Beacon Alpha.

  Anthropic increased the weekly limits for Cloud Code, which faces criticism as third-party agents were simultaneously moved to a separate, paid API credit system. This leads to higher costs for developers and is criticized as lacking transparency and addressing infrastructure problems.

  Further updates include the introduction of a fast mode for Cloud Code, an upcoming major update to Google’s Jewels, and continuous improvements to Hermes Agent, a self-improving open-source AI agent. Additionally, Figure AI presented an impressive robot demo featuring humanoid robots working autonomously in a warehouse.

  The video explicitly discusses Google’s Gemini, OpenAI’s GPT, Anthropic’s Cloud Code, and open-source tools like Hermes Agent. It addresses intermediate and advanced users interested in the latest developments and technical details in the AI industry.

• Hermes Agent v2.0! Huge New Updates: WebUI, Qwen 3.6 Plus FREE, Computer Use, & More!
  13.5.2026, 05:08:59

  The video presents the latest updates to Hermes Agent, an open-source AI agent that continuously evolves and can be run on your own infrastructure. Key new features include:

  1. **Computer Use Feature**: Hermes can now control the computer in the background without taking over PC control. Currently works only on macOS, but support for Windows and Linux is planned. The feature is compatible with various AI models like Claude, GPT-4, Gemini, and local open-source models.

  2. **Integration of Alibaba’s Qwen 3.6 Plus**: This powerful model is now integrated into Hermes and offers long context windows and multimodal capabilities. It’s free for a limited time.

  3. **Light Panda Integration**: An integrated, open-source browser backend specifically developed for AI workflows. It provides improved browser automation and reliability.

  4. **Kanban Board**: A new Kanban board enables creating unlimited boards and projects, orchestrating multiple agents, and managing tasks through a dashboard.

  5. **/goal Command**: A long-term autonomous goal mode function that continuously plans, executes, verifies, and retries on errors until the goal is achieved.

  Additionally, minor updates like voice cloning and multilingual support were introduced. The video recommends Tiny Fish for web automation tasks and points to Hermes’ open-source nature, making it a versatile tool for AI workflows.

  The video explicitly discusses Hermes Agent, open-source models, Tiny Fish, and is better suited for intermediate to advanced users.

• Claude Code Agent View IS INSANE! Huge New Update Introduces /goal, sessions, & More!
  12.5.2026, 07:03:39

  The video presents the latest updates to Anthropic’s Cloud Code, a tool for agent-based development. Key new features include:

  1. **Agent View**: A central interface for managing all Cloud Code sessions. This enables running and managing multiple coding sessions in parallel in a single dashboard. Users can switch between sessions without losing context and run background tasks.

  2. **/goal Feature**: A function enabling autonomous executions with a defined goal. The agent works independently until the goal is achieved and is usable in various workflows and on mobile devices.

  3. **/radio and Claude FM**: An integrated lo-fi radio station intended to enhance user experience.

  4. **Improved System Prompt Compaction**: Prompt trimming was optimized to better preserve sensitive instructions and user intent without showing explicit warnings when context is shortened.

  The video discusses the benefits of these updates, particularly for complex, agent-based coding workflows, and mentions the possibility of using Depot CI for faster and more consistent CI/CD pipelines. However, it critically notes Cloud Code’s limited token usage, which could restrict practical applicability.

  Final Comment: The video explicitly discusses Claude (Anthropic) and Depot CI and is intended for intermediate to advanced users.

• Hermes Agentic OS is The Future
  11.5.2026, 07:07:11

  The video introduces Hermes Agent, an open-source project from Mistral AI conceived as a persistent autonomous system that continuously learns and evolves over time. It can run 24/7 on your own infrastructure, build long-term memories, develop reusable skills, and gain deeper understanding of the user. The author shows how Hermes Agent combined with ION UI can be further developed into an agentic OS (AIOS) capable of managing multiple autonomous AI agents executing complex multi-step tasks without constant human supervision. ION UI is a free open-source co-work platform enabling AI agents like Hermes to work directly on the user’s computer, reading and managing files, writing and executing code, browsing the internet, automating workflows, and working alongside the user as a co-worker. The video demonstrates installing and configuring Hermes Agent and ION UI, as well as various use cases such as creating a financial dashboard in Excel, organizing desktop files, and creating a report on rural EV charging infrastructure. The author emphasizes the system’s ability to execute multiple tasks simultaneously and continuously improve, making it a powerful tool for automation and efficiency enhancement.

  The video explicitly discusses Hermes Agent and ION UI and is better suited for intermediate and advanced users.

AI and Strategy | Le SamourAI (1 new video)

• AI costs 85% less this week. You need to act on it.
  27.4.2026, 14:59:21

  The video analyzes strategic movements in AI infrastructure and models, particularly the impact of Deepsic V4’s launch in collaboration with Huawei. It draws a historical parallel to the Swiss watch industry and Japanese quartz technology to illustrate current dynamics in the AI market. Deepsic V4 is an open-source model specifically optimized for Huawei’s Chinese hardware, representing an alternative to US-dominated solutions like Nvidia and CUDA. The video discusses the strategic implications of this development, including potential impacts on OpenAI and Anthropic, as well as long-term effects on the AI market and the labor landscape.

  The video explicitly covers Deepsic V4, Huawei, OpenAI, Anthropic, Nvidia, CUDA, and Google. It’s geared toward Intermediate and Advanced audiences.

Matt Pocock (6 new videos)

• I stopped using /grill-me for coding. Here’s what I use instead:
  14.5.2026, 14:22:56

  The author introduces a new tool called “Grill with Docs,” an improved version of the previous “Grill Me” skill. The original “Grill Me” skill interviews the user to reach shared understanding and make decisions step by step. However, the author found that “Grill Me” often took too much time and didn’t document all relevant information. That’s why he developed “Grill with Docs,” which uses a shared language (Ubiquitous Language) from Domain-Driven Design to improve communication between user and AI. This new tool searches for a “context.md” file that documents the shared language and updates it during the session. It helps sharpen unclear language, discuss concrete scenarios, and link them to code. The author demonstrates using “Grill with Docs” in a practical example and shows how it improves communication efficiency and clarity with the AI. He emphasizes that “Grill Me” remains useful, but “Grill with Docs” is better suited for projects with an existing codebase.

  The video explicitly features Claude AI models and is aimed at intermediate or advanced users.

• Anthropic's "dedicated monthly credit" is actually a huge cut
  13.5.2026, 20:12:51

  The video addresses the problem of AI-accelerated software entropy, where codebases decay faster because changes are often made without considering the entire codebase. The author presents his method for rescuing such codebases by relying on software fundamentals and his improved codebase architecture skill. He explains key concepts like modules, interfaces, implementations, deep and shallow modules, dependency graphs, seams and adapters, which come from John Ousterhout’s book “A Philosophy of Software Design.” Deep modules are particularly valuable because they hide much implementation behind a simple interface, thus improving maintainability and utility. The author demonstrates applying these concepts to his own codebase by using the “Improve Codebase Architecture” skill in Claude to identify and implement improvements. He emphasizes the importance of testing and the need for strategic decisions by the developer, since AI agents can be tactically effective but require strategic guidance. The video is aimed at intermediate to advanced developers who want to improve their codebases and leverage the benefits of deep modules. (Claude, Intermediate/Advanced)

• New Skills! /handoff, /prototype, /review and /writing-* | Skills Changelog
  12.5.2026, 09:56:10

  The video showcases the latest updates and improvements to a repository of AI skills that recently reached 70,000 stars on GitHub. The main additions are two new skills:

  1. **Handoff skill**: This skill creates a handoff document that summarizes the current conversation so a new agent can continue the work. The document is stored in a temporary file and contains suggestions for skills that should be used in the next step. The skill is particularly useful for switching between different context windows without losing important information. There are two main use patterns: “Fire and Forget” and “DIY Sub Agent.”

  2. **Prototype skill**: This skill helps with creating prototypes, particularly in UI development and creating logic prototypes for stateful applications. The skill generates multiple UI variants and allows testing and refining them interactively before implementation.

  Additionally, some bugfixes were presented, including an improvement to the “Grill with Docs” skill through the use of XML tags to control information prioritization, and adjustments to the “To PRD” and “To Issues” skills to use the correct labels.

  There’s also a preview of two skills in development: one for writing text (Tripart skill) and one for code reviews. The Tripart skill helps structure text fragments into a complete story or article, while the Code Review skill checks adherence to coding standards and correct implementation of requirements.

  Finally, a documentation website is mentioned that contains videos for each skill and a newsletter to stay updated on the latest developments.

  The video explicitly features Claude and is aimed at intermediate to advanced users.

• Burn through the backlog from hell with /triage
  7.5.2026, 15:00:43

  The video introduces a tool called “Triage,” specifically designed for processing GitHub Issues and other backlogs. It helps transform unstructured ideas and bug reports into clear, actionable tasks that can be handled by AFK agents (autonomous AI agents). The tool uses a state machine system with two categories (Bug and Enhancement) and five states (e.g., “needs triage,” “ready for agent,” “won’t fix”) to clearly classify each issue. Users can go through individual issues or the entire backlog to categorize them and fix them directly if needed. The video shows a live demo where the creator applies the tool to his own repository “Sank Castle” to triage issues and even fix them directly. The integration with other skills, such as the “Diagnose” skill, which automatically reproduces and fixes bugs, is also demonstrated. The tool is designed to facilitate collaboration between human developers and AI agents by providing a clear structure for task management.

  The video explicitly features Claude and is aimed at intermediate or advanced users who already have experience with GitHub, backlog management, and working with AI agents.

• I Open-Sourced My Own AFK Software Factory
  30.4.2026, 13:28:38

  The video shows how to orchestrate AI coding agents in isolated sandboxes using the TypeScript library “Sand Castle” to run them completely autonomously (AFK). The author explains that he tried various solutions but encountered issues with Docker sandboxes. So he developed Sand Castle, which allows controlling agents with simple TypeScript functions. The video demonstrates setting up Sand Castle in a repository, selecting an agent (e.g., Claude Code) and a sandbox (e.g., Docker), and using GitHub Issues as a backlog manager. It shows how to create a Docker image, set required environment variables, and create a GitHub Issue for the agent to work on. The author explains the structure of the main.ts file, which orchestrates different agents (Planner, Implementer, Reviewer, Merger), and how these agents work in parallel and merge code commits. At the end, it’s shown how the agent creates a TypeScript template with tests and CI scripts and merges the changes into the main branch.

  The video explicitly features Claude (Anthropic), Docker, and GitHub and is aimed at intermediate or advanced users.

• How To De-Slop A Codebase Ruined By AI (with one skill)
  29.4.2026, 15:09:12

  The video addresses the problem of AI-accelerated software entropy, where codebases decay faster because changes are often made without considering the entire codebase. The speaker presents a method to rescue such codebases by relying on software fundamentals and improved codebase architecture. He explains key concepts like modules, interfaces, implementations, deep and shallow modules, seams, and adapters. Deep modules, which hide much implementation behind a simple interface, are highlighted as advantageous. The speaker demonstrates applying these concepts to a real codebase by using Claude’s “Improve Codebase Architecture” skill. This skill identifies improvement opportunities and guides the user through a process to structure and test the codebase. The speaker emphasizes the importance of testing and deep modules for long-term codebase health and recommends applying the skill regularly.

  The video explicitly features Claude and is aimed at intermediate to advanced developers.

Coding with Lewis (8 new videos)

• How Meta Went From Open Source Hero to AI’s Biggest Villain
  15.5.2026, 15:04:55

  The video tells the story of Meta and its open-source AI model Llama, which was released in 2023 and was downloaded over a billion times within two years. Meta was praised for its open and accessible approach to AI, which allowed developers to use the model on their own hardware and build upon it. Llama 2 and Llama 3 followed, demonstrating impressive performance, with Llama 3.1 even competing with the best closed-source models from OpenAI and Google. However, Meta’s success was overshadowed by the release of DeepSeek v3 by a Chinese AI lab, which achieved similar performance at a fraction of the cost. This created pressure on Meta to release Llama 4, which ultimately led to a disaster. Llama 4 was released on a Saturday without warning and revealed three models, one of which, Behemoth, was still under development. The claimed performance of Llama 4 was quickly questioned when developers and researchers discovered that the models didn’t live up to the promises and that Meta had used manipulated benchmarks. The community responded with disappointment and distrust, and Meta lost the trust it had built over years. The story demonstrates how important honesty and transparency are in the open AI community and how quickly trust can be lost.

  The video explicitly addresses Meta’s Llama models and is aimed more at intermediate or advanced viewers.

• How a GitLab engineer DESTROYED their main database…
  13.5.2026, 17:12:24

  The video tells the story of a severe data loss at GitLab in 2017, when an engineer accidentally deleted the production database. The engineer was attempting to fix a replication issue during a spam attack and mistakenly deleted the primary database instead of the secondary one. This caused the entire platform to go down, as all backup systems failed. GitLab was only able to restore a six-hour-old staging server snapshot, resulting in the loss of six hours of user data. The recovery was streamed live, with over 5,000 viewers watching the process. GitLab subsequently published a detailed post-mortem report, which is considered one of the most transparent in the tech industry. The incident highlights the importance of regular backup testing and the need to review backup strategies.

  The video addresses GitLab and is aimed more at intermediate and advanced users.

• The software that powers EVERY video online
  11.5.2026, 17:12:28

  The video introduces FFmpeg, a free and open-source tool used for processing video, audio, and other media formats. Developed in 2000 by Fabrice Bellard, FFmpeg can convert, cut, compress, stream, and remix virtually any media format. Despite its complex command-line interface, it is used by major tech companies. In 2011, a governance debate led to the fork of Libav, which was later abandoned. FFmpeg is operated by a small group of developers without external funding and remains a central tool in media processing.

  The video explicitly addresses FFmpeg and Libav, and is more suitable for intermediate and advanced users.

• The Crazy History of Docker 🐳
  1.5.2026, 17:16:43

  The video explains the importance of Docker for software development and how it solved the problem of incompatibility between local and server environments. Released in 2013, Docker allows developers to package applications and all necessary dependencies into a container, so the application runs identically everywhere. Although Docker didn’t invent containers, it made the technology accessible through simple Dockerfiles and commands. Within two years, Docker reached a million downloads and received support from major companies like Microsoft and Google. However, Docker lost the orchestration war against Kubernetes, and Docker Swarm lost prominence, which led to financial difficulties. Nevertheless, the core tools survived, and Docker remains a standard tool for developers that simplifies complex Linux kernel functions.

  The video addresses Docker and Kubernetes and is aimed more at intermediate and advanced developers.

• The Code Inside Everything (That Gets Zero Credit)
  30.4.2026, 14:34:52

  The video tells the story of SQLite, the most widely used yet least known software in the world. SQLite was developed by Richard Hipp, a contract engineer who was frustrated by the frequent outages of the Informix database on the USS Millinocket (DDG 79), where he worked. He decided to write his own database that doesn’t require a separate server instance but reads directly from a file. SQLite was born.

  The software was initially released as an open-source project and quickly gained popularity, especially after being deployed on devices like the PalmPilot and later on mobile phones from Motorola and AOL. A pivotal moment was the integration of SQLite into the Android operating system, which led to explosive growth. Despite its enormous success, the team behind SQLite remained small, consisting of only three people who handled all development and maintenance.

  The video highlights SQLite’s unique philosophy, which aims to avoid dependencies and maintain control over the project. This led to a strict policy of not accepting external code contributions, which is viewed both as a strength and a weakness. While this ensured SQLite’s stability and reliability, it also prevented the integration of new features requested by the community.

  Some developers, including Glauber Costa and Pekka Enberg, decided to fork SQLite and create their own version called LibSQL, which follows a more open contribution model. They argue that SQLite’s rigid structure hinders its further development. However, Richard Hipp remains committed to his philosophy and emphasizes that he wants to continue developing SQLite his way.

  The video explicitly addresses SQLite and its developers, particularly Richard Hipp. It is aimed more at intermediate and advanced users, as it delves into technical details and the software’s history.

• Where does “404 Not Found” even come from?
  29.4.2026, 16:33:44

  The video explains the origin of the HTTP status code 404 “Not Found” and debunks the myth that this code was inspired by a room at CERN headquarters. Instead, it explains that 4xx codes are reserved for client errors. More interesting than the technical origin is the cultural evolution of the 404 error: many companies use the 404 page as a design opportunity to add creative and entertaining Easter eggs, such as GitHub with a Star Wars parallax scene or Pixar with the character “Sadness” from “Inside Out”.

  The video addresses HTTP status codes and their cultural reception, and is more suitable for a broad audience (beginner to intermediate).

• What a Billion Database Rows Look Like in Real Life
  24.4.2026, 15:10:21

  The video illustrates the physical size of databases by converting the number of rows into stacks of paper. It starts with 50 rows on one sheet of paper and scales up to a billion rows, which corresponds to a stack higher than any building in Canada. The comparison shows that a database with a million rows is roughly two meters high, while a database with 100 million rows would be about as high as the Eiffel Tower. The video also explains how databases like Postgres use indexes to query data quickly and compares this to manually searching through stacks of paper. Real examples like Spotify, Uber, and Facebook are mentioned, which generate enormous amounts of data daily. The video emphasizes the efficiency of databases compared to physical storage media and promotes Supabase as a platform for using Postgres.

  The video explicitly addresses Postgres and Supabase and is aimed more at intermediate and advanced users.

• The Humble History of 7Zip
  23.4.2026, 16:52:13

  The video introduces 7-Zip, software that has been available for free since 1999 and was created by a single developer, Igor Pavlov, from Russia. 7-Zip uses the LZMA compression algorithm developed by Pavlov, which at the time was superior in terms of compression ratio and file size. The .7z file format can compress files 30 to 70 percent better than the .zip format depending on the data type. The algorithm has been adopted by various projects, including the Linux kernel, Android firmware images, and game installers. Despite an outdated user interface design, 7-Zip remains popular because it is efficient and free.

  The video explicitly addresses 7-Zip and is more suitable for intermediate or advanced users interested in efficient compression tools.

Julian Goldie SEO (10 New Videos)

• New Update Makes Claude 10X More Powerful
  21.5.2026, 05:30:24

  The video introduces the latest Claude update, specifically designed for small businesses to significantly boost their productivity. With the new feature, users can leverage tools like QuickBooks, HubSpot, PayPal, or Canva to create automated workflows, personalized morning reports, or complete marketing campaigns in seconds. Concrete use cases include accounting, where Claude reconciles transactions, flags errors, and creates a clean summary for the tax accountant. Payroll processing is also simplified, with Claude generating a 30-day forecast and drafting reminder emails. For marketing purposes, Claude pulls sales data, develops a strategy, and creates content directly in Canva. Tasks that previously would have kept an entire team busy can now be completed with a single release click.

  The video explicitly addresses the Claude AI model and targets intermediate users who are already familiar with basic business tools.

• New Google AI Studio Update Is INSANE!
  21.5.2026, 05:00:10

  The video presents the new features of Google AI Studio, a free browser tool that lets users create apps through simple English descriptions. The key updates are:

  1. **Integration with Google Workspace**: Apps can now access and edit Gmail, Google Sheets, Docs, Drive, and Calendar. Google AI Studio automatically handles the complex configuration of permissions and security handshakes.

  2. **Creation of native Android apps**: Users can build real Android apps with Kotlin and Jetpack Compose that work offline and can access hardware sensors like GPS, Bluetooth, and camera. Apps can be tested in an embedded Android emulator and transferred to real devices via USB.

  3. **Free web deployment**: Apps can be deployed to Cloud Run at no cost, receive a stable HTTPS endpoint URL, and scale automatically, including scaling down to zero when not in use. API keys remain securely managed.

  4. **Enhanced AI features**: Google AI Studio’s “Anti-Gravity Agent” maintains the context of the entire project, manages multiple files, and reviews its own work to reduce hallucinations. There’s also an annotation mode that lets you adjust UI elements through simple descriptions.

  The video emphasizes that this technology now enables non-programmers to quickly and easily create useful tools, which can lead to significant time savings. However, it notes that apps are currently intended for personal use only and not for publication to a broad audience.

  The video explicitly addresses Google AI Studio, Gemini, and Google Workspace and is geared toward intermediate and advanced users.

• New Google Project Genie Update is Mind Blowing!
  21.5.2026, 03:00:05

  The video covers the latest updates to Google’s Project Genie, now connected to 20 years of Google Street View data. This integration allows users to explore real locations in AI-generated versions, selecting different styles and scenarios. The host emphasizes that Project Genie isn’t just an entertainment tool but strategically important to Google, as it’s used by Waymo for simulating self-driving cars. The technology enables real-time generation and exploration of actual places, useful for applications like real estate, tourism, and training. The host warns against viewing the technology as merely a toy and stresses the importance of real data for AI model development. He concludes with a call to familiarize yourself with Google’s AI tools and use them early to gain a competitive advantage.

  The video explicitly addresses Google’s Project Genie, Street View, and Waymo and is geared toward intermediate and advanced users.

• OpenClaw 5.19 Update Just Dropped…
  21.5.2026, 02:17:19

  The video presents the new features of OpenClaw 5.19, which significantly expand the capabilities of AI agents. Key updates include the Custom-Plugin-Builder, which allows creating custom tools for agents without programming knowledge, and five new Skills, including a meme maker, diagram builder, and Python debugging tool. The Android app has been enhanced with real-time voice functionality, and Grock is now available for free through the OpenClaw subscription. Further improvements affect the Mac app, browser, Telegram integration, and sub-agents functionality. The video recommends creating a backup before updating and promotes an Agentic Operating System that combines OpenClaw, Claude, and Hermes in one dashboard.

  The video explicitly addresses OpenClaw, Claude, Grock, and Hermes and targets intermediate and advanced users.

• New Gemini App: Automate & Build ANYTHING!
  21.5.2026, 01:00:22

  The video introduces Google’s new Gemini app, which goes far beyond a simple chatbot. The app offers several innovative features, including Gemini Spark, Daily Brief, a new design, and the fast Gemini 3.5 Flash. Gemini Spark acts as a 24/7 assistant that completes tasks in the background, such as answering emails, creating documents, or conducting research. Daily Brief summarizes important information from emails, calendars, and tasks each morning. The new design improves user experience, and Gemini 3.5 Flash delivers faster and smarter processing. The video demonstrates practical applications, such as creating content, planning weeks, and automating routine tasks. It emphasizes the benefits of adopting this technology early and invites viewers to try the app and join the AI Profit Boardroom community to dive deeper into using AI tools.

  The video explicitly addresses Google Gemini and is geared toward intermediate and advanced users.

• NEW Google Flow Update is INSANE!
  21.5.2026, 00:00:36

  The video presents the latest Google Flow update, transforming the platform into a comprehensive creative studio for filmmakers and content creators. Key updates include integration of three separate tools (Flow for video, Whisk for visual moodboards, and ImageFX for image generation) into a unified workspace. This enables seamless creation of image collages, high-quality images, and animated videos without switching between different tools. Additionally, image generation with the Nano Banana model is now integrated free of charge into Flow, and existing projects from Wisp or ImageFX can be transferred to the Flow library. Asset management has been improved with search, filter, and sort functions, as well as the ability to group assets into collections and reference them in prompts using the @ symbol. New editing features include the lasso tool for precise image editing, video clip extension, object insertion and removal in videos, and camera movement control. The updated VO3.1 video model offers improved audio features and better audio-video integration. The video emphasizes that Google Flow is now a complete creative studio, spanning from concept through to finished, audio-accompanied video. Flow TV is also highlighted as a free learning resource.

  The video explicitly addresses Google Flow, Nano Banana, and VO3.1 and is geared toward intermediate and advanced users.

• NEW Google Stitch Updates are INSANE!
  20.5.2026, 23:00:31

  The video presents the latest updates to Google Stitch, an AI-powered design tool that lets you create app designs through voice or text input. Key updates include:

  1. **Streaming functionality**: Stitch builds designs on the canvas in real time, so users can follow the process and pause to make changes.
  2. **Editing existing designs**: Users can upload existing designs, such as Figma files or screenshots, and Stitch builds on them while maintaining the style.
  3. **In-place AI edits**: Users can adjust individual design elements directly without regenerating the entire design.
  4. **Motion on the HTML-native canvas**: Stitch now supports animations and hover effects directly on the canvas, based on real HTML and CSS code.
  5. **Import and export options**: Designs can be exported as Figma files, published directly to Netlify, or imported into tools like Lovable and Bolt to add backend functionality.
  6. **Codebase sync**: Users can connect their codebases with Stitch to integrate design changes directly into the code.

  The video also shows practical use cases and provides tips for effectively using Stitch. It emphasizes that Stitch is now a true production tool that seamlessly connects design and code.

  The video explicitly addresses Google Stitch, Lovable, Bolt, Google Anti-gravity, Claude Code, and Cursor and is geared toward intermediate and advanced users.

• NEW Google Pomelli Updates are WILD!
  20.5.2026, 21:00:58

  The video presents the latest updates to Google Pameli, an AI tool developed specifically for small businesses, creatives, and brands. The three main features are:

  1. **Pameli Agent**: An AI-powered brand strategist that plans colors, fonts, tone, and campaigns. Users simply input their website or ideas and receive a complete branding strategy within seconds.

  2. **AI website generator**: Pameli can create complete websites that match your brand. Users simply specify what the website should accomplish, and Pameli creates a finished website with layout, images, and text.

  3. **Brand books**: Pameli generates complete brand books in under a minute, defining colors, fonts, image styles, and brand tone. This helps ensure consistent brand identity.

  The video emphasizes that these updates could revolutionize how brands are built and managed by accelerating and simplifying the process. However, it also notes that Pameli is still in beta, and the quality of results depends on the quality of inputs.

  The video explicitly addresses Google Pameli and is geared toward intermediate and advanced users who already have experience with AI tools and want to integrate them into their business.

• How to Build a Self Improving Agentic OS in Claude
  20.5.2026, 20:00:09

  **Summary:**

  The video introduces Agent OS, a locally hosted dashboard that connects various AI agents such as Claude, Hermes, and OpenClaw and enhances their learning capabilities through a central knowledge base in Obsidian. Agent OS enables an integrated work environment where all agents can access shared goals, notes, and projects, increasing efficiency and personalization. The creator demonstrates two use cases: creating an SEO ROI calculator and a sales page, both in HTML, both quickly and efficiently implemented through agent use. Installing Agent OS requires setting up Hermes, Ollama for local models, and Obsidian as a knowledge store. The dashboard can be built with Claude and specific prompts in Next.js and Tailwind. The creator also offers a ready-made solution in the AI Profit Boardroom that provides additional resources and support for implementation.

  **Final comment:**
  The video explicitly addresses Claude, Hermes, OpenClaw, and Obsidian and targets intermediate users who want to use their AI tools more efficiently.

• Google Spark just changed AI Agents forever!
  20.5.2026, 19:00:19

  The video introduces Google Spark, a new AI agent that performs tasks in the background, even when your devices are turned off. Spark can interact with Google tools like Gmail, Calendar, Drive, Docs, Sheets, Slides, YouTube, and Google Maps. Users can assign Spark tasks, set schedules, and teach it how to complete tasks in their personal style. The agent works autonomously, but the user maintains control over access and permissions. Examples of applications include summarizing emails, creating to-do lists, and updating documents based on new emails. The agent is currently in limited testing but will be available to more users in the coming weeks. The video emphasizes the importance of familiarizing yourself with such tools early to save time and become more productive.

  Final comment: The video explicitly addresses Google Spark and is geared toward intermediate and advanced users who are already familiar with Google tools.

Kyle Balmer | AI with Kyle (10 new videos)

• There are three ways to use AI, and most people only use one of them
  20.5.2026, 07:44:06

  The video discusses three fundamental ways people use artificial intelligence, based on an AI Fluency course from Anthropic. The first method is automation, where users ask AI like Claude directly to perform tasks or answer questions, expecting the AI to complete them. This is the most common but also the weakest use of AI, as results are often mediocre. The second method is augmentation or co-intelligence, where users combine their own expertise with AI to achieve better results. A simple example is asking the AI to ask questions and work together on a solution. The third and most advanced method is new agency, where users set the AI a goal and give it the freedom to determine the best way to achieve it. This requires fewer detailed instructions and allows the AI to research and act independently.

  The video explicitly discusses Anthropic’s Claude model and is more suited for intermediate users.

• How I’d Build an AI Product and Quit My Job If I Started Today
  20.5.2026, 05:00:10

  The video provides guidance on building your first AI-based business. The focus is on creating a simple but valuable product that automates a specific task and saves time. The author emphasizes that while many people could create similar solutions themselves, they won’t due to convenience or lack of knowledge. The key to success is identifying a process that’s common and time-consuming in your own industry and automating it. An example given is an AI maturity assessment where users answer questions and receive a personalized report in return. Technically, building such a product is divided into three layers: frontend (landing page, login, forms), backend (database for user data and results), and the logic layer where actual data processing occurs. The author offers to provide a prompt template that can be used in tools like Codex or Claude to ease product development. The focus should be on the logic layer since that’s where the greatest customer value is created.

  The video explicitly discusses Claude, Codex (OpenAI), and Lovable, and is intended for intermediate and advanced users.

• Anthropic just said prompting is only 25% of using AI well
  19.5.2026, 11:44:57

  The video addresses the four competencies for effective AI use, as defined by Anthropic, the developers of Claude. These competencies, referred to as “the four Ds,” include delegation, description, discernment, and diligence. Delegation refers to deciding when and how to use AI and includes three main modes: automation, augmentation, and agency. Description is the art of prompting, communicating clearly to the AI what you expect from it. Discernment refers to the ability to evaluate and verify the AI’s results, while diligence encompasses the ethical and responsible aspects of AI use. The video emphasizes the importance of an iterative process between description and discernment to achieve high-quality results.

  The video explicitly discusses Claude from Anthropic and is aimed at intermediate users.

• Can you spot fake AI Art? What’s wrong with this Monet that was created by AI? This was a question
  18.5.2026, 11:41:39

  The video discusses reactions to an experiment where an authentic Claude Monet painting was disguised as AI-generated artwork. The upload on Twitter led to a wave of negative comments criticizing the image quality as “school level,” “lacking coherent composition,” and “emotionless.” Many users later deleted their comments after learning it was a genuine Monet work. This reaction shows that rejection of AI-generated art is often based on prejudice and emotional reactions rather than informed artistic consideration. The incident undermines arguments against AI art by exposing the subjective and often biased perception of art.

  The video doesn’t explicitly discuss AI models and providers, but addresses general perceptions of AI-generated art and is more suited for intermediate and advanced viewers.

• Codex Mobile: You Can Now Vibe Code From Anywhere (Seriously)
  18.5.2026, 05:00:13

  The video covers the launch of a mobile application for ChatGPT Codex, enabling users to continue their Codex sessions from anywhere. The main points are:

  – **New mobile app**: Codex is now available in the ChatGPT mobile application, allowing users to start new work, review outputs, and control execution.
  – **Device connection**: Users can connect their Codex sessions across different devices (laptop, Mac Mini, phone) and access them from anywhere. This is done by scanning a QR code and using the “Control Another Device” feature in Codex settings.
  – **Benefits**: The new feature solves the problem of users losing chat threads and context when switching between devices. This enables seamless “vibe coding” from anywhere.
  – **Setup guide**: The speaker explains how to connect various devices and set up GitHub as a central repository for projects. He emphasizes the importance of keeping all applications up to date.
  – **Recommendation**: The speaker recommends trying out the new feature and signing up for the newsletter to receive detailed guidance and a checklist.

  The video explicitly discusses ChatGPT Codex and is intended for intermediate users already familiar with AI tools.

• AI has a lot of problems
  17.5.2026, 16:41:56

  The video addresses the discussion about an AI data center’s water consumption of 29 million gallons. The author argues that while this figure seems large, it’s negligible compared to other industries like meat production, particularly burger manufacturing. The data center’s water consumption equates to roughly 40,000 to 45,000 burgers, which represents only 0.03% of the 50 billion burgers produced annually in the US. The author criticizes public attention on AI data center water consumption as exaggerated and distracting from larger environmental problems in other industries like meat and fast fashion.

  The video doesn’t discuss specific AI tools or models and addresses a broader audience interested in environmental issues and technology’s impact.

• The 4 AI Skills Anthropic Wants You to Have (Explained in 20 minutes)
  15.5.2026, 05:00:02

  The video summarizes Anthropic’s “AI Fluency” course, designed to help you work effectively, efficiently, ethically, and safely with AI systems. The course is divided into three main use cases: automation (handling tasks following instructions), augmentation (collaborating with AI as a sparring partner), and agency (AI working independently toward a set goal). The core of the course lies in the four “Ds”: delegation (deciding which tasks to delegate to AI), description (clearly communicating the task), discernment (critically evaluating AI output), and diligence (ethical and responsible use). Particular emphasis is placed on the “description to discernment” loop, where AI output is continuously reviewed and improved to achieve high-quality results. The course advises against hastily automating tasks, instead recommending testing and refining in an augmented mode first. Diligence includes checking AI use for accuracy, transparency, and verification to avoid ethical and practical errors.

  The video explicitly discusses Claude from Anthropic and is intended for intermediate and advanced users.

• Selling to people who already trust you is one of the easiest business moves on earth
  14.5.2026, 18:45:34

  The video argues that most entrepreneurs approach product launches incorrectly by creating a product and then releasing it to a non-existent audience. Instead, the focus should be on first building an existing target audience that will readily adopt the product. The speaker emphasizes the importance of content creation and social media presence, not for vanity but as a strategic lever for trust, reach, and partnerships. He shares his own experience building a community of 300,000 people in two years and generating over $500,000 in revenue, arguing that artificial intelligence significantly streamlines this process by handling much of the content creation. However, he warns against delegating all content creation to AI, and demonstrates his own system, which combines human and AI-generated content. He offers guidance on such a system, which interested parties can obtain by commenting or through his TikTok bio.

  The video discusses generic AI tools for content creation and is intended for intermediate and advanced entrepreneurs.

• Full AI automation kills your content
  14.5.2026, 15:45:26

  The video argues against fully automating content creation with AI, warning that purely AI-generated content is penalized by algorithms long-term and will be overtaken by more professional providers. Instead, the speaker advocates using AI as a tool to amplify your own voice and personality. He demonstrates his own system where an AI agency suggests topics, creates outlines, and transforms his spoken notes into a presentation. This presentation is shared in a live stream on platforms like YouTube and TikTok, with a focus on remaining authentic and personal. From the livestream transcript, he uses Claude Code to generate various content formats such as newsletter drafts, scripts for short videos, PDFs, and social media graphics, which he then manually edits and publishes. The speaker offers guidance on setting up a similar system in various AI models like Claude Code, Open Claude, Hermes, or Code X.

  The video explicitly discusses Claude Code, Open Claude, Hermes, and Code X and is intended for intermediate users.

• I watched Anthropic’s entire AI Fluency course so you don’t have to
  20.5.2026, 14:45:56

  The video introduces free AI courses from Anthropic, the company behind the Claude AI model. These courses are high quality and offer certifications. The video author takes the viewer through an evaluation of the courses to show which ones are worthwhile and which are too demanding. He offers to complete the courses himself and summarize the key content to save viewers time. For the first course on “AI Fluency,” a link is provided if viewers leave the keyword “fluency” in the comments.

  The video explicitly discusses the Claude AI model from Anthropic and is suitable for beginners and intermediate users.

David Shapiro (3 new videos)

• Techno-feudalists hate UBI
  23.4.2026, 16:55:48

  The video discusses the attitude of the so-called “Tech Right” toward universal basic income (UBI) and presents their arguments against UBI before refuting them. The “Tech Right” is described as a group of Silicon Valley types, often venture capitalists or founders, who tend to be pro-MAGA, pro-Trump, and pro-military-industrial complex. Notable representatives include Mark Andreessen and Gil Verdon.

  The main arguments of the Tech Right against UBI are:
  1. UBI flattens incentive gradients, which reduces motivation for ambitious goals.
  2. UBI prevents maximizing entropy generation, i.e., the creation of useful new information.
  3. UBI hinders civilization’s ascent on the Kardashev scale.
  4. UBI leads to dependence on the state and is therefore harmful.

  The author refutes these arguments as follows:
  1. Many of history’s greatest entropy generators, such as Bill Gates, Steve Jobs, and Charles Darwin, had financial security that gave them room for creativity and innovation.
  2. UBI is not high enough to destroy incentives for additional work and still provides enough incentive to earn more.
  3. UBI promotes advancement on the Kardashev scale by increasing demand and thus stimulating innovation and energy generation.

  Furthermore, the author criticizes Mark Andreessen’s philosophical and moral arguments, which are based on Protestant work ethic and emphasize the necessity of work without considering the negative aspects of wage slavery.

  The video explicitly addresses the views of Mark Andreessen and Gil Verdon and is aimed more at intermediate and advanced viewers.

• Why chatbots always get worse
  21.4.2026, 11:38:31

  The video discusses user dissatisfaction with current chatbots, particularly with Anthropic’s Opus 4.7, and compares the problems to those of social media. The author argues that similar incentive structures found in social media also lead to deterioration of the user experience with chatbots. Three main incentive structures are identified: cost control, avoidance of litigation, and user-friendliness. These result in chatbots becoming less emotionally intelligent and often appearing annoying or overcritical. The author compares this to the “shitification” of technologies, where they get worse over time, and argues that users themselves are often the weakest link, which exacerbates the problems. He concludes by noting that companies could solve these problems better but haven’t made the right adjustments so far.

  The video explicitly addresses Anthropic, OpenAI, and Gemini and is aimed more at intermediate or advanced users.

• I’m worried about where things are going
  20.5.2026, 10:35:09

  The video discusses the impending development toward “techno-feudalism,” in which human intelligence becomes redundant through artificial intelligence (AI). The speaker warns of the emergence of “redundant biomass,” where humans could be degraded to economically useless, disposable beings. He argues that this development is driven by several overdetermined forces, including geopolitical competition between the USA and China, capitalism and neoliberal economic policy, as well as the rational economic decision for cheaper automated solutions. Although the speaker is techno-optimistic and sees the potential of automation for positive developments, he emphasizes the urgent need to address the political and social implications of this development.

  The video explicitly addresses AI and automation in general, without naming specific tools or models, and is aimed at an intermediate to advanced audience.

AI News & Strategy Daily | Nate B Jones (10 new videos)

• How ChatGPT Became Teenagers’ Best Friend #AI #Psychology
  May 20, 2026, 03:00:16

  The video discusses the increasing use of AI companion chatbots by teenagers for emotional support, often as a primary source of emotional connection. While these chatbots are always available, patient, and non-judgmental, they lack the ability to teach genuine interpersonal skills like conflict resolution, relationship resilience, and empathy. The lack of real interaction can lead to parasocial relationships that can end tragically in extreme cases. In everyday life, the simplicity and immediacy of AI assistance promotes dependency, making it harder for children to solve problems independently and thus go through genuine learning processes. The video warns that AI doesn’t actively diminish children’s intelligence, but rather deprives them of the opportunity to take more difficult but more educational paths.

  The video addresses generally available AI chatbots and is aimed at a broad audience, particularly parents and guardians.

• The calculator moment nobody’s talking about in education #AIinEducation #Learning #Parenting
  May 20, 2026, 00:00:00

  The video discusses the urgent need for educational system reform in light of rapid AI development. It argues that current educational concepts are based on outdated philosophy designed for a 20th-century industrial economy that no longer exists today. The speaker emphasizes that 2 billion children worldwide are in schools that don’t recognize or leverage these changes. Studies, such as one published in the journal Nature, demonstrate that general AI has already arrived, and show that AI tutors outperform human tutors in controlled studies. Despite these developments, schools, governments, and parents still lack clear strategies for preparing children for future challenges. Growing use of AI in education, particularly in countries like the United Kingdom, underscores the urgency of these adaptations.

  The video explicitly addresses AI tools and models in general without naming specific providers and is aimed at a broad audience, including parents, education professionals, and interested parties—more suited to Intermediate and Advanced viewers.

• Google Spent a Year Stitching MCP, A2A, AG-UI Together. I/O Today.
  May 19, 2026, 14:01:16

  The video discusses six agent protocols introduced over the past twelve months that support agent systems. The protocols are MCP, A2A, AGUI, A2UI, AP2, and X42. The speaker argues that three of these protocols—MCP, A2A, and AGUI—will become a core stack for agent systems, while the other three (A2UI, AP2, and X42) remain disputed or highly specific to certain domains.

  MCP (Multi-Client Protocol) is a tool and data layer that enables agents to discover and utilize systems where work takes place. A2A (Agent-to-Agent) is a coordination layer that allows agents to communicate with other agents across product or organizational boundaries. AGUI (Agent-Generated User Interface) is a human-machine interface layer that allows long-lived backend agents to share state, events, permissions, and interruptions with a user-facing application.

  The speaker emphasizes that these protocols shape customer experience and that understanding them is important when developing an AI agent product. He also warns that tool access is not simply a feature toggle but a security boundary that must be carefully configured.

  The video is suited for Intermediate or Advanced viewers, as it discusses technical details and specific protocols. While specific AI tools or models aren’t explicitly addressed, it covers Google and its role in developing these protocols.

• 40% growth nobody saw coming #expansion #tech
  May 19, 2026, 03:00:36

  The video shows a conversation about the growth of a platform used by both coding and non-coding users. The user base recently crossed the 4 million mark and continues to grow at an accelerating rate, with the goal of soon reaching 5 million users. Particularly noteworthy is that usage by non-coding users is growing faster than overall user growth, with 40% growth recorded in the past week compared to the previous week. This suggests that the platform is increasingly being used for general purposes and not just for coding tasks.

  The video doesn’t address specific AI tools or models and is more suited for Intermediate or Advanced users interested in platform growth and user behavior.

• The biggest lie you’ve heard about AI jobs #ai #futureofwork #shorts
  May 19, 2026, 00:00:33

  The video discusses the changing dynamics between human work and artificial intelligence. It argues that as AI capabilities increase, the boundary between human and machine work doesn’t shrink but grows. This leads to more interfaces where human judgment is required, as well as new challenges in verification and decision-making. Unlike traditional skills that are learned once and completed, working at the interface between humans and AI requires continuous adaptation as this boundary constantly expands.

  The video generally addresses the dynamics between humans and AI and is more suited for Intermediate or Advanced viewers.

• The Prove-It Economy is Here | And Most Marketers Aren’t Ready
  May 18, 2026, 14:00:17

  The video discusses the shift of the internet economy from an attention economy to an interpretation economy dominated by AI systems. The speaker emphasizes that individuals and marketers must adapt to this change as AI systems increasingly determine whether you’re trustworthy. A concrete example is purchasing a sound system, where the speaker interacted exclusively with AI chatbots (Claude and ChatGPT) to make the best choice.

  For marketers, this means creating a “truth layer” for their products that enables AI agents to extract high-quality and precise data. This requires technical details and verifiable claims that go beyond emotional marketing appeals. Individuals must also build such a truth layer for themselves to demonstrably present their skills and experience, particularly regarding AI capabilities.

  The speaker warns against “AI-washing,” the mere pretense of AI competence, and emphasizes the need to be clear and differentiated for both humans and AI agents. He concludes by encouraging investment in two areas: creating memorability with humans and providing differentiated, detailed information for AI agents.

  The video explicitly addresses the AI models Claude and ChatGPT and is more suited for Intermediate and Advanced viewers.

• How teams accidentally sabotage AI adoption #ai #aitools
  May 18, 2026, 03:00:24

  The video discusses a common failure scenario in implementing coding agents in enterprises. It criticizes an overly pragmatic, top-down approach that attempts to predetermine all permissible use cases. Instead, the speaker advocates giving employees the freedom to figure out what works in their respective areas. What’s important is creating a platform where successful “recipes” can be quickly shared and distributed. This would allow best practices to establish themselves throughout the organization.

  The video addresses general concepts and no specific AI tools or models, and is more suited for Intermediate or Advanced viewers.

• When to Automate, Build, Buy, Hire, or Wait on AI
  May 17, 2026, 18:00:14

  The video discusses challenges and strategies for investing in Agentic AI projects, particularly in light of Gartner’s prediction that over 40% of these projects will fail by the end of 2027. The main reason for this prediction lies in unclear business models, high costs, and insufficient risk controls. The speaker emphasizes that the focus shouldn’t be on the technology itself but on designing the workflows supported by AI. He argues that companies should align their investments based on the type of work that needs to be done, not on the technology or vendor.

  The speaker provides several examples to illustrate that different workflows require different solutions. He suggests that companies should categorize their workflows into five categories: Automate, Build, Buy, Hire, and Wait. Each of these categories has its own advantages and disadvantages and should be selected based on the specific nature of the work. The speaker also emphasizes the importance of clearly defining workflows and expectations for AI solutions to ensure investments deliver desired value.

  Toward the end of the video, an investment matrix is presented to help companies make decisions about their AI investments. The matrix considers the specificity of the work and the maturity of market solutions. The speaker concludes by calling on companies to understand their workflows thoroughly and make targeted investment decisions to maximize value from their AI investments.

  The video explicitly addresses Agentic AI projects and is more suited for Intermediate and Advanced viewers.

• Cognitive Architecture Beats AI Detection Every Time #ai #education #parenting
  May 21, 2026, 00:00:11

  The video discusses the impossibility of reliably detecting AI use in student work. AI researcher Andrej Karpathy is quoted, clarifying that detecting AI-generated text is mathematically not correctly implementable. The speaker criticizes the use of AI detection tools in schools, which disadvantage students based on false results. He argues that educational systems must rethink their methods instead of relying on unreliable detection tools. The core message is that a fundamental redefinition of assessment criteria is necessary.

  The video addresses generally available AI tools and is aimed at Intermediate and Advanced viewers.

• These 5 Infrastructure Giants Secretly Rule AI
  May 20, 2026, 14:01:40

  The video discusses the critical infrastructure companies that determine whether AI agents can be deployed in production, not the model makers like OpenAI or Anthropic. Companies like Cloudflare, Stripe, Octa, Ozero, and Data Dog play a central role despite not developing models. These companies control the infrastructure that determines where agents run, on whose behalf they act, what they know and can spend, and who can stop them. The video emphasizes that while physical computing power is important, it’s not sufficient to successfully deploy agents. Various control layers are examined, including runtime environments (Cloudflare, AWS, Vercel), identity management (Ozero, Octa, Work OS, Microsoft Entra), data control (Snowflake, Databricks), payment processing (Stripe, credit card networks), and observability (Data Dog, Langsmith, Brain Trust, Langfuse). Additionally, the importance of kill-switch mechanisms is highlighted. The video recommends analyzing and clarifying these control layers for specific agent workflows before moving them to production. It emphasizes that agents can bypass existing permission structures, leading to governance challenges. Final takeaway: The video addresses a variety of infrastructure companies and is more suited for Intermediate and Advanced viewers.

Alejandro AO (5 new videos)

• MiniMax Agent: Alternative to ChatGPT + Codex?
  12.5.2026, 12:46:44

  The video showcases the features of MiniMax Agent, an AI tool positioned as a competitor to Codex and Cloud Cowork. MiniMax Agent is powered by the MiniMax M2.7 model, which, while not as powerful as GPT-5.5 or Opus 4.7, still achieves high benchmark scores and is offered at a more affordable price.

  The video demonstrates how to use MiniMax Agent to create a website and deploy it on MiniMax Cloud. It introduces both the web and desktop app of the tool. The desktop app is used for data analysis of a CSV dataset, generating a PDF report with LaTeX. Additionally, the “Skills” of MiniMax Agent are showcased, including a video story generator that creates videos from text descriptions or images.

  The video also mentions MiniMax’s pricing models, which include a free version with daily credits as well as premium plans. Particular emphasis is placed on the tool’s ability to handle complex tasks such as website creation, data analysis, and video generation.

  Final note: The video explicitly focuses on MiniMax Agent and is aimed more at intermediate and advanced users.

• Pi Agent – Crash Course | Minimal Coding Agent
  6.5.2026, 06:17:00

  The video introduces Pi Agent Harness, a minimalist agent harness that can be customized to meet user needs. The focus is on enabling users to get started quickly without covering all features in detail. The key points are:

  1. **What is Pi?**
  – Pi is a minimalist agent harness that starts with just four core functions and can be individually customized through extensions and modifications.
  – Unlike other agent harnesses, Pi does not provide pre-built features such as MCP (Multi-Chat-Persistence), subagents support, planning mode, or integrated to-do lists. Instead, these features can be added as needed.

  2. **Installation and Basic Setup**
  – Installation is done via a simple command in the command line.
  – After installation, users need to log in with an API key or subscription (e.g., from Hugging Face, Anthropic, ChatGPT, or GitHub Copilot) to use LLMs (Large Language Models).
  – Models can be selected via the `/model` command and switched between different providers.

  3. **Model Selection and Customization**
  – Users can choose between different models and save them in favorite lists.
  – The thinking level of the model (e.g., low, medium, high) can be adjusted.

  4. **Prompt Templates**
  – Custom prompts can be created and saved to simplify frequently used commands.
  – These prompts are stored in the `.pi` directory structure and can be manually edited.

  5. **Skills**
  – Skills are functions that extend the agent harness. They can be loaded from various directories, including `.agents` and `.clod`.
  – Skills can be invoked and used via the `/skill` command.

  6. **Themes and User Interface**
  – The Pi user interface can be modified by customizing themes.
  – Custom themes can be created and stored in the `.pi` directory structure.

  7. **Context Files**
  – Pi uses the standards `agents.md` and `clod.md` for context management.
  – These files can be stored in various directories (e.g., workspace or home directory) and loaded by Pi.

  8. **Extensions**
  – Extensions enable customization and expansion of Pi’s functionality.
  – Example extensions include welcome messages and security prompts before dangerous commands (e.g., `rm -rf`).

  9. **Packages**
  – Packages are bundles of extensions, skills, and prompts that can be installed together.
  – Examples of packages are `PySubagents`, `ContextMode`, and `MCPAdapter`.

  10. **Sessions**
  – Sessions enable management, editing, and navigation of threads.
  – Sessions can be named, exported, and saved in various formats.
  – Users can switch between different sessions, duplicate them, or merge them.

  The video explicitly focuses on Pi Agent Harness and is aimed more at intermediate users who already have experience with agent harnesses and want to customize them individually.

• DeepSeek V4: SOTA Coding Agent at 12x Lower Cost
  28.4.2026, 09:43:58

  The video introduces the new DeepSeek V4 Pro and DeepSeek V4 Flash models from DeepSeek, a major Chinese AI company that sparked the open-source revolution for large language models in 2025 with its R1 model. The new models are Mixture-of-Experts models that operate more efficiently through selective parameter activation. Comparison with other state-of-the-art models such as GPT-5.5 from OpenAI and Opus 4.7 from Cloud shows that DeepSeek V4 Pro performs very well in various benchmarks including coding, general reasoning, and agentic capabilities, sometimes even outperforming GPT-5.4 and approaching GPT-5.5. Particularly noteworthy is DeepSeek’s significantly lower pricing compared to closed models. The video also demonstrates the installation and use of DeepSeek V4 Pro via the Pi Agent harness, a minimalist agent framework, and shows the creation of a web application as an example of practical application.

  The video explicitly addresses DeepSeek V4 Pro and V4 Flash as well as GPT-5.5, Opus 4.7, Gemini 3.1 Pro, Kimi K 2.6, GLM 5.1, and Minimax M 2, and is aimed at intermediate users.

• GPT-5.5 – 25x More Expensive than Open Models
  23.4.2026, 23:13:53

  The video provides an overview of OpenAI’s latest version, GPT-5.5, and compares it with other models, both closed and open-source. The author emphasizes that GPT-5.5 delivers the best results in various benchmarks, particularly in coding tasks such as Terminal Bench and SweetBench Pro. However, GPT-5.5 is significantly more expensive than its predecessor GPT-5.4 and other models like Claude Opus 4.7 and Gemini 3.1 Pro. The comparison with open-source models like Kimi, GLM, Minimax, and Qwen 3.6 shows that these often deliver similar performance at significantly lower costs. The author also demonstrates the use of GPT-5.5 in the Codex application to create a landing page, showing that the model has improved in frontend development.

  The video explicitly addresses OpenAI (GPT-5.5, GPT-5.4), Claude (Claude Opus 4.7), Gemini (Gemini 3.1 Pro), and open-source models (Kimi, GLM, Minimax, Qwen 3.6) and is aimed more at intermediate and advanced users.

• Kimi K2.6: Open Source BEATS GPT-5.4 & Opus?
  22.4.2026, 06:17:00

  The video introduces the new foundation model Kimi K2.6 from Chinese company Muncho Taiyai, which competes with benchmarks like GPT 5.4 and Opus 4.6. The host explains what Kimi K2.6 is, compares benchmarks, and shows how to use the model with Hugging Face Inference Provider to operate a coding assistant. Kimi K2.6 is then used to redesign a website’s design. The benchmarks show that Kimi K2.6 outperforms GPT 5.4 and Opus 4.6 in several areas, particularly in general knowledge and programming. The host demonstrates setting up Kimi K2.6 with OpenCode and Hugging Face to redesign the website and shows the final result. The cost for using the model is estimated at approximately $1.50 for the entire operation. The video explicitly addresses Kimi K2.6, Hugging Face, OpenCode, GPT 5.4, Opus 4.6, and Gemini 3.1 Pro and is aimed more at intermediate and advanced users.

Sebastien Dubois (4 new videos)

• Levels of AI Context Management: From Generic Answers to Precision Results
  16.5.2026, 08:48:32

  The video discusses various levels of context management when using AI, particularly when interacting with language models like GPT or Claude. The speaker distinguishes eight levels, ranging from simple queries without context (level 1) to a comprehensive knowledge system that can be fully utilized by AI (level 8). In the early stages (1-3), the focus is on providing basic context and leveraging the built-in memory functions of AI, though these are described as unreliable and pseudo-random. From level 4 onwards, advanced prompt engineering techniques are introduced, which yield better results but come with challenges such as organizing and managing prompts. Starting at level 5, the importance of a centralized knowledge system containing information about projects, goals, and work processes is emphasized. This enables AI to deliver more precise and relevant results. In the higher stages (6-8), the focus shifts to managing AI memory, implementing AI agent capabilities (skills), and optimizing context management to improve consistency and quality of results. The speaker emphasizes that a well-structured knowledge system that can be fully understood and utilized by AI currently delivers the best results.

  The video explicitly addresses Claude, OpenAI, and specific tools such as Obsidian, Anthropic, Google, and OpenAI. It is geared toward intermediate and advanced users.

• Why Obsidian
  13.5.2026, 22:00:35

  The video describes Obsidian as an operating system for Markdown files. It enables easy writing, editing, and using of notes, including integration with AI. A major advantage of Obsidian is that all data is stored locally on your own device, ensuring privacy and control over your content. Unlike many other note-taking tools, Obsidian remains free and the files belong to the user. The video emphasizes the comprehensive features for organizing, searching, and utilizing stored information.

  The video focuses on Obsidian and is better suited for intermediate and advanced users.

• Use AI to augment yourself, not to replace your thinking!
  13.5.2026, 09:41:05

  The video criticizes the trend of creating AI-generated graphs in Obsidian that often consist of meaningless masses of notes. The main point is that AI should not be used to generate meaningless content, but rather to support your own knowledge building. Writing is a process of thinking, and if you don’t do this yourself, you end up with only useless texts. The focus should be on creating your own notes and developing your own ideas, rather than relying on AI-generated content.

  The video addresses Obsidian and AI tools in general, but is better suited for intermediate users who engage with the concept of knowledge management.

• Knowledge Management
  13.5.2026, 09:07:53

  The video introduces the concept of knowledge management, which aims to free your mind by no longer relying on memory but instead using systems that permanently store information and make it easily retrievable. The core idea is that by utilizing such systems, you are able to easily retrieve everything you have stored. The speaker emphasizes that this method works and has the potential to transform your life.

  The video does not address specific AI tools or models and is better suited for beginners.

Unsupervised Learning (1 new video)

• A Conversation With Brian Vecci
  13.5.2026, 15:00:14

  The video is an interview with Brian, a data security expert at Veronis, focusing on the challenges and solutions related to AI security.

  Brian explains that conversations with customers and security teams have shifted significantly over recent years from general uncertainty about AI to concrete questions about safely deploying AI tools like ChatGPT, Claude, and Microsoft Copilot. Today, the focus is on how companies can leverage AI to work more efficiently while ensuring appropriate “safe zones” are in place to minimize security risks.

  He emphasizes that AI significantly expands the attack surface, as attackers can use AI to identify and exploit vulnerabilities. Veronis has developed a comprehensive solution based on three pillars: observability, automation, and behavioral monitoring. This solution includes data capture and analysis, access rights monitoring, and automated security measures.

  Brian highlights that many organizations still don’t fully understand the complexity and risk associated with AI security. He warns that attackers are increasingly using AI to breach systems quickly and efficiently, emphasizing the need to secure data and the underlying infrastructure.

  The video concludes with a discussion about implementing the Veronis solution, which is fast and effective, and announces that Veronis will present further AI security updates at the Black Hat conference.

  Final comment: The video explicitly addresses AI models like Claude, ChatGPT, and Microsoft Copilot, as well as specific tools like Veronis AI Atlas. It’s geared toward intermediate and advanced audiences, as it provides in-depth insights into AI security and complex solution approaches.

---

Automatically generated from the latest YouTube videos of the curated channel selection. For feedback, suggestions, or to unsubscribe: simply reply to this email.