From Night Work to Linux Vulnerabilities: A Week of Technical Deep Dives
Wednesday, May 13, 2026
🎧 Podcast Episode (4.2 min)
Hello, this weekly newsletter guides you through the most important new videos from a curated selection of AI and Coding YouTube channels. One compact summary per video, plus a daily overview of dominant topics. If interested, simply click the link below the summary.
This week focuses heavily on automation and operating systems. Brian Casel demonstrates in several videos how AI agents can be leveraged for night work to automate routine tasks. Claude Code is particularly highlighted, as it can access local capabilities and files not available in the cloud version. The convergence of various developer tools toward plan-based development (spec-driven development) is also discussed, with Claude Code, Cursor, and Codex taking center stage.
Another central topic is operating system security. Fireship provides a detailed explanation of how a critical security vulnerability in the Linux kernel was discovered by an AI tool. The video demonstrates the importance of AI tools for improving code quality, citing Code Rabbit as an example. Additionally, the current GitHub crisis is discussed, characterized by increasing outages and technical problems. Alternatives such as GitLab, Codeberg, and Source Hut are mentioned.
Beyond the technical deep dives, there are also practical tips. NeuralNine offers a comprehensive introduction to JavaScript for beginners and shows how to use the ONNX format to export machine learning models to a universal format. The newsletter also covers how to install Open Claw on a virtual private server (VPS) with Ubuntu and connect it to Telegram. Another video argues for the benefits of tech content creation and knowledge sharing, while another demonstrates how to create a simple Slack bot with Python.
A special highlight is the video on FastEmbed, a Python library specifically optimized for local embedding creation. The video shows how to generate text and image embeddings and calculate similarity between sentences using vector distances. Overall, a week full of technical insights and practical applications.
Brian Casel (3 new videos)
- How I build agents that work the night shift
12.5.2026, 12:01:07The video introduces the concept of “Night Shift,” a method for deploying AI agents to handle recurring business tasks. The author describes how he uses agents to automatically complete tasks during his absence (e.g., overnight), such as checking and optimizing SEO metadata on his website or reviewing pull requests in his open-source GitHub projects. The process consists of three main components: a shared interface (e.g., a markdown file or custom app), human feedback during short, focused sessions, and an AI agent executing a skill on a fixed schedule. The author emphasizes that the actual effort lies in setting up the system, but the long-term benefits come from automating and delegating routine tasks.
The author demonstrates two concrete examples: an agent that checks and updates SEO metadata as needed, and another that reviews GitHub pull requests and provides recommendations for merging or closing requests. In both cases, the author receives reports that he briefly reviews and provides feedback on before the agent proceeds with next steps.
The video explicitly features Claude and OpenAI, and is geared toward intermediate to advanced users who already have experience with AI agents and are ready to develop their own systems and processes.
- Why You Need Claude Code Server Mode?
6.5.2026, 14:01:40The video shows how Claude Code can leverage locally installed skills and files that are unavailable in the cloud version. The user demonstrates how he uses various custom-built skills on his local machine that are stored directly on his file system. This enables extended functionality since Claude Code can access these resources locally, which isn’t possible in the web version. The advantage is that tasks requiring access to local files or installed skills can be completed more efficiently.
**Closing comment:** The video explicitly covers Claude Code and is intended for intermediate users already familiar with local development environments.
- Why Every AI Coding Tool is Converging on Plan Mode?
1.5.2026, 14:01:11The video demonstrates how various developer tools are adopting the trend toward plan-based development (spec-driven development) and integrating it as a standard feature. The author illustrates this using a product requirements document (PRD) for a customer portal, which he uses with three tools – Claude Code, Cursor, and Codex – to create an implementation plan. In Claude Code, Plan Mode is automatically activated, guiding the user through a series of questions to create a detailed plan. In Cursor, Plan Mode is accessed via Shift+Tab, highlighting the standardization of this feature across different tools. The author emphasizes that this convergence of tools facilitates adoption and switching between them.
The video explicitly features Claude Code, Cursor, and Codex, and is aimed at intermediate to advanced users familiar with spec-driven development.
Niklas Steenfatt
No new videos in this period.
Fireship (3 new videos)
- Every operating system concept in one video…
7.5.2026, 17:32:34The video provides a detailed explanation of how an operating system works from the moment the power button is pressed until shutdown. It starts with the bootloader loading the OS, then progresses through various stages including privilege levels, virtual memory, file systems, device drivers, and interrupts. The kernel builds the system, manages processes and memory, enables inter-process communication, and ensures system security and stability. The video also highlights the importance of system calls, schedulers, and threads. At the end, it describes the shutdown process where all processes are terminated and the system shuts down safely.
The video does not focus on specific AI tools or models and is aimed more at intermediate viewers seeking a deeper understanding of operating systems.
- 732 bytes of Python just borked every Linux machine on earth…
4.5.2026, 18:40:40The video covers a critical security vulnerability in the Linux kernel known as “copy fail” (CVE-2023-31431), which has existed since 2017 and was discovered by an AI tool. The vulnerability allows a local unprivileged user to gain root access to a Linux system by writing four controlled bytes into the page cache of a read-only file. The exploit leverages a weakness in the AF_ALG interface and affects all Linux distributions updated after 2017. While the vulnerability is not remotely exploitable, it requires updates across all affected systems. The video explains the technical details of the exploit and emphasizes the importance of AI tools for improving code quality, with Code Rabbit cited as an example.
The video explicitly addresses AI tools such as the AI agent tool used by Theori and Code Rabbit, and is aimed at intermediate to advanced users.
- GitHub is having some major issues right now…
30.4.2026, 16:37:31The 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 software development platform. GitHub, founded in 2008 and acquired by Microsoft in 2018 for $7.5 billion, is indispensable for many developers. However, outages and technical issues have become increasingly frequent, leading to massive dissatisfaction within the developer community. The video creator mentions several incidents, such as accidental deletion of pull requests, search functionality outages, and critical security vulnerabilities. A particularly striking example is the decision by Mitchell Hashimoto, a prominent developer, to migrate his open-source projects away from GitHub, which is viewed as a sign of growing frustration among many developers.
The video creator analyzes the causes of these problems and points to the increasing strain from AI agents heavily taxing the platform. Despite the criticism, he emphasizes that Microsoft and GitHub are working to improve the situation. Alternative platforms to GitHub include GitLab, Codeberg, and Source Hut. The video concludes with an appeal for choosing a meaningful and fulfilling career, supported by the organization 80,000 Hours.
The video addresses GitHub and Microsoft, and is aimed at an intermediate to advanced audience.
NeuralNine (7 new videos)
- JavaScript Crash Course: Full Beginner Tutorial
13.5.2026, 16:01:18The video provides a comprehensive introduction to the fundamentals of JavaScript programming. It starts with basic concepts like outputting text to the console and using variables. The author explains the differences between the keywords `let`, `var`, and `const` as well as their scopes. Various data types such as numbers, strings, booleans, and special values like `undefined`, `null`, `Infinity`, and `NaN` are covered. The author also demonstrates how to work with operators, including arithmetic, assignment, comparison, and logical operators.
Furthermore, control structures such as `if-else` statements and `switch-case` constructs are explained. The author demonstrates how to process user input with the `readline` library. Various loop constructs like `while`, `do-while`, and `for` loops are introduced, including the use of `break` and `continue` to control loop execution.
Functions and their usage are explained in detail, including function definition, the use of parameters, return values, anonymous functions, lambda expressions, and the use of functions as first-class objects (callbacks). The author also shows how to work with arrays, maps, and sets, as well as the definition and use of objects and classes in JavaScript.
Finally, it is briefly shown how JavaScript can be embedded in HTML to create interactive web pages.
The video is suitable for beginners with basic programming knowledge who are looking for a quick but comprehensive introduction to JavaScript. No specific AI tools or models are discussed.
- ONNX: The PDF Format For Neural Networks
11.5.2026, 16:00:44The video demonstrates how to use the ONNX format (Open Neural Network Exchange) to export machine learning models into a universal format that runs independently of the original frameworks like PyTorch or TensorFlow. The author demonstrates this with simple examples where a model that increments a number by one is created in both frameworks and then exported to the ONNX format. It then shows how to use the exported model with ONNX Runtime without requiring PyTorch or TensorFlow. A more complex example with an MNIST classifier trained in PyTorch and exported to ONNX format is also presented. Finally, it is demonstrated how to download and use a model from Hugging Face in ONNX format. The author emphasizes the advantages of interoperability and reduced dependencies through using the ONNX format.
The video explicitly discusses ONNX, PyTorch, TensorFlow, Hugging Face, and ONNX Runtime and is aimed at intermediate to advanced users.
- Why you should start creating tech content…
10.5.2026, 11:04:45The video argues for the benefits of tech content creation and knowledge sharing. First, teaching forces deep understanding because you must explain concepts clearly and simply, similar to the Feynman Technique. Additionally, you can directly connect new knowledge with teaching and thereby expand your portfolio. Second, consistent content creation demonstrates proactivity and discipline, which employers and partners view positively. Third, reach and recognition open doors, as large followings are often associated with competence, even though this shouldn’t be the main motivation. The author emphasizes that tech knowledge should be shared, even without a camera, such as through blogs or LinkedIn.
The video does not discuss specific AI tools and is aimed at intermediate and advanced tech experts considering sharing their knowledge.
- OpenClaw: Simple VPS Setup Guide
8.5.2026, 16:00:03The video shows step by step how to install Open Claw on a virtual private server (VPS) with Ubuntu and connect it to Telegram. First, a VPS is set up at Hetzner and Ubuntu is installed. Next, Node Version Manager (NVM) is installed to use the required Node.js version (24). Open Claw is installed globally and the onboarding process is started. OpenAI is selected as the model provider and Telegram as the communication channel. After entering the OpenAI API key and Telegram bot token, the bot is configured and started. The bot can then be addressed via Telegram to perform tasks such as creating and editing files. The video emphasizes the security risks of Open Claw and recommends running it in an isolated environment.
The video explicitly discusses OpenAI, Telegram, and Open Claw and is aimed at intermediate users.
- Coding Slack Bots in Python: Quick Start Guide
4.5.2026, 16:00:21The video shows how to create a simple Slack bot with Python. It focuses on creating a Minimal Viable Product (MVP) that can execute commands and communicate with a language model (LM). The process begins with setting up a Slack app and creating a bot in a Slack workspace. Then, a Python project is set up with the necessary packages (python-dotenv and Slack-Bolt). The bot is programmed to respond to specific messages, execute commands, and reply to mentions. As an example, it is shown how to connect the bot to the OpenAI API to get responses from GPT-4O. The video demonstrates the basic functionality of the bot and how to use it in a Slack channel.
The video explicitly discusses the use of OpenAI (GPT-4O) and is aimed at intermediate users.
- How to stay up-to-date in AI/ML?
3.5.2026, 22:40:53The video offers tips on how to stay updated on the latest developments in AI and machine learning in just 15 minutes per day. The author recommends three main strategies: First, read Hacker News, as it regularly publishes current articles and discussions on new models, frameworks, and papers. Second, subscribe to the right YouTube channels, such as Fireship for quick updates and AI Explained for in-depth analysis. Third, engage with like-minded people and join communities to automatically receive relevant news. The author emphasizes that these methods provide natural filtering and deliver only the most relevant information.
The video discusses Hacker News, YouTube channels like Fireship and AI Explained, as well as communities and is suitable for intermediate to advanced users.
- FastEmbed: Local AI Embeddings in Python
1.5.2026, 16:00:07The video introduces the Python library FastEmbed, which is specifically optimized for local embedding creation, even on less powerful systems without dedicated GPUs. FastEmbed uses ONNX Runtime to avoid dependencies like PyTorch or TensorFlow, and offers a simple and fast way to work with text and image embedding models.
The tutorial shows the installation of FastEmbed and demonstrates the creation of text embeddings using an example with three sentences that compare different meanings of “Apple” and “Microsoft”. It shows how to calculate similarity between sentences using vector distances. Subsequently, the use of image embedding models with two example dog images is explained.
Additionally, it is explained how FastEmbed is implicitly used by Qdrant, a vector store optimized for filtering and custom tagging. Finally, the possibility of GPU usage with FastEmbed is briefly discussed, with emphasis that this does not happen automatically and requires additional configuration.
The video explicitly discusses FastEmbed and Qdrant and is aimed at intermediate users.
Automatically generated from the latest YouTube videos of the curated channel selection. For feedback, suggestions, or to unsubscribe: simply reply to this email.