Letting Codex Agents Commit: Making .git Writable in the workspace-write Sandbox
Codex CLI's workspace-write sandbox lets the agent edit anything in your repo -- except commit. Every git commit dies with:
Learning Machine
machina discendi
Latest posts
The Dark Arts of Web Automation
Ominous, right?
How I Fixed Handy's Memory Leak Without Knowing Rust
I applied The Framework to diagnose and fix a nasty memory leak in the wonderful Handy voice transcription app. This required some novel adaptations of The Framework that Software and AI Engineers alike will appreciate.
Unlocking Codex GPT-5.4's Full 1M-Token Context Window
Update (July 2026): as of Codex 0.144.4, this technique no longer works -- the model_context_window override is now ignored, and context ceilings are enforced server-side. See the full update at the end of this post.
Getting Handy to work in GNOME Wayland (Ubuntu 25.10+)
Handy (CJ Pais's Tauri 2.x speech-to-text desktop app, v0.8.3 Linux AppImage) is the chosen dictation tool. The required workflow:
Is HTML "Strictly Better" Than Markdown for Claude Code?
Thariq Shihipar of Claude Code team fame posted an article last week, "The Unreasonable Effectiveness of HTML" , arguing that Claude should output HTML files by default for basically everything. PR reviews, postmortems, status reports, the lot. It's a good piece, racked up 8.3M views, and most of it I …
The Web Is Now a Two-Way Street for AI
Yohan Lasorsa, Developer Advocate at Microsoft, and Olivier Leplus, Developer Advocate at AWS, opened their joint talk with a premise most web developers already accept: AI helps you build websites. Their argument is that the reverse is now equally true -- the web is becoming AI's runtime, its data source, and …
Your Digital Exhaust Is the Most Underused Dataset You Own
Šimon Podhajský ( LinkedIn , X ), Head of AI at Waypoint AI, opened with a premise that cuts against the grain of most personal AI demos: what if the most valuable thing an AI can do with your data is simply read it?
Your Multi-Agent System Isn't Failing Because of the AI
Sandipan Bhaumik ( LinkedIn ), Data & AI Tech Lead at Databricks, opened with an anecdote that set the tone for the whole talk. A single credit-scoring agent ran for two weeks in production without issues. The team added four more agents. Within days, 20% of risk ratings were wrong -- not because the …
Your LLM Evaluator Is Probably Lying to You
Mahmoud Mabrouk ( X , LinkedIn ), co-founder and CEO of Agenta AI, opened his AI Engineer Europe workshop with a scenario most teams will recognize: your LLM agent is in production, your observability dashboard looks clean, but customers keep saying the thing doesn't work. The culprit, he argues, isn't the agent -- it's …
When Every Team Builds Its Own AI Agent, You Need a Registry
Sonny Merla, Mauro Luchetti, and Mattia Redaelli ( Quantyca ) opened with a question that any large organization experimenting with AI agents will recognize: what happens when dozens of teams across multiple continents are all building agents independently?
RAG Isn't Dead, You Just Need a Better Starting Point
Phil Nash ( X , LinkedIn ), a developer relations engineer at IBM, opened his AI Engineer Europe talk by taking aim at the "RAG is dead" discourse. His counter is simple: if every business had less than a million tokens of data, maybe. But they don't, and not everyone wants to pay …
AI Agents Can't Walk Upstairs and Ask for Help
Juan Herreros Elorza ( LinkedIn , GitHub ), Team Lead on the Cloud Native Technology team at Banking Circle, makes a deceptively simple argument: the platform engineering practices that have always been "best practices" are now prerequisites. Not because they've changed, but because AI coding agents have become first-class users of internal developer …
Fitting the Model Isn't the Same as Running It Well
Mozhgan Kabiri Chimeh ( LinkedIn ), a developer relations manager at NVIDIA, opened her AI Engineer Europe talk with the pain point that drives most AI developers to the cloud: you either run out of memory or you don't have the right software stack. The result is that development iteration speed depends …
The Real Problem Is the Six Minutes After the Call
Dippu Kumar Singh ( LinkedIn ), Leader of Emerging Technologies at Fujitsu North America, presents a talk that starts where most AI discussions stop. Most generative AI demos assume clean text input. In a contact center, the data starts as messy, overlapping, emotionally charged audio -- and the engineering challenge isn't transcription. It's …
AI-Generated Code Is Just Untrusted Code From the Internet
Harshil Agrawal ( X , LinkedIn ), a Senior Developer Educator at Cloudflare, opened his AI Engineer Europe talk with a reframe that should be obvious but apparently isn't: strip away the branding, and the code your LLM writes deserves exactly as much trust as code you found on a random website. Which …
The Security Cliff Between Local and Production MCP
Tun Shwe ( LinkedIn ) and Jeremy Frenay ( LinkedIn ), both AI Engineers at Lenses.io , gave a joint talk at AI Engineer Europe 2026 on what happens when MCP servers leave the safety of a developer's laptop. Their central claim: most MCP servers are built for single-player local development and collapse the …
Your AI Agent Is a Junior Developer. Manage It Like One.
Brendan O'Leary ( LinkedIn , X ), a Developer Relations Engineer at Kilo Code , opened his AI Engineer Europe talk with a observation that's easy to nod along with and hard to act on: most engineers have used AI tools by now, but almost none of them can articulate how they actually work …
MCP Tools Are Raw Material, Not Finished Products
Nimrod Hauser ( LinkedIn , X ), a founding engineer at Baz, opened his talk at AI Engineer Europe with a deceptively simple observation: public MCP servers ship tools designed for everyone, which means they're optimized for no one. When you plug generic tools into a production agent, the agent hallucinates URLs, saves …
Build the Gym, Not the Dataset
Stefano Fiorucci ( X , LinkedIn , GitHub ) is an AI/Software Engineer at deepset, where he contributes to the open-source LLM framework Haystack. At AI Engineer Europe 2026, he made a case that the next leap for open-source language models isn't better datasets -- it's better environments. The kind where models can act …
Subagent Modes in Claude Code
A post making the rounds claims that Claude Code subagents share a prompt cache, making parallelism "basically free." It says you can spin up five agents and pay barely more than one. It lists three execution models — fork, teammate, and worktree — and says they all share the cache. Analysis of …
Remapping the Logitech R500s on Ubuntu 24.04 with keyd
Here’s my latest keyboard:
The Cure for the Vibe Coding Hangover
A practical framework for building software with AI agents.
WTF is BM25? The Intuition Behind the Algorithm
BM25 is an unsung hero powering heaps of stuff you use every day – think search bars, recommendation systems, or even those fancy AI chatbots that somehow dig up the right info from a mountain of text (we're looking at you, Retrieval-Augmented Generation).
⚡️ Latent Space - The new OpenAI Agents Platform
OpenAI have dropped their new Agents Platform. Swyx and Alessio chat with Nikunj Handa and Romain Huet of OpenAI to discuss the release.
The Python Lambda Tutorial You Never Asked For
Let's be real, nobody wakes up in the morning thinking, "You know what I need more of in my life? Python lambda functions." But here we are. Buckle up, because this is the lambda tutorial you didn't ask for -- but secretly need.
Founders #383: Todd Graves' $10B Chicken Finger Dream
I listened to Senra's great episode on Todd Graves of Raising Cane's fame this morning. Here are my snips from the episode.
How to Add Custom HTML Pages to a Pelican Site
Pelican is a powerful static site generator written in Python, primarily designed for blogs. However, sometimes you need to include custom HTML pages that don't fit into Pelican's standard content model. This guide explains how to add standalone HTML pages to your Pelican site while preserving their exact formatting and …
AI Engineer Summit 2025: Agents at Work
AI Engineer Summit 2025 Agents at Work Event: AI Engineer Summit 2025: Agents at Work When: February 19 - 22, 2025 Where: New York Focus: Practical implementation of AI agents in production environments Executive Summary The 2025 AI Engineer Summit marked a pivotal transition from theoretical AI capabilities to practical implementation reality. We've had unprecedented advances in foundation…
Using the BytesIO Class in Python
The io.BytesIO class in Python is an in-memory stream for binary data. It provides a file-like interface that lets you read and write bytes just like you would with a file, but all the data is kept in memory rather than on disk. This can be extremely useful when …
Linking to Posts in Python Pelican
Pelican provides a syntax for linking to another post by its filename.
Copying Files in Linux With a Progress Bar
I’ve long used rsync for high fidelity, detailed copies of large swathes of files in Linux. For example:
Why An 8TB Drive Isn’t 8 Usable TB
I bought an 8TB external SSD to use as a live boot Linux device. I knew that this issue was due to the way that bits are aggregated into terabytes, but — thanks to our mate ChatGPT — here’s a nice explanation of why my 8TB SSD only shows 7,452 …
Wrap with HTML tags in VSCode
Using the Emmet capabilities in VSCode (see previous TIL) you can highlight a section of HTML code and quickly wrap it with other HTML using Emmet shortcuts.
__main__.py file in a project
This is, to a Python project / module, what if __name__ == '__main__ is to an individual Python file.
A nice workflow for creating Python projects with AI
First, create a new project using poetry
neofetch for Linux system info summary
neofetch provides a nice snapshot of system information. This is what you were wanting to add to the --sysinfo output for gpt-engineer .
Emmet Abbreviations in VSCode
Apparently there’s this plugin for many IDEs called Emmet which makes writing HTML very fast!
Installing Racket (Scheme) in WSL
We’ll install Racket from apt as follows, as the snap version ended up with many hassles
raco: Racket's Package Management System (and More)
In the Racket programming language, raco is a command-line tool used to interact with Racket's package management system, run tests, build documentation, and perform other tasks related to Racket development. It's a versatile utility that automates various tasks in Racket projects.
Working through SICP in Jupyter Notebooks
I’m reading Structure and Interpretation of Computer Programs and want to write Racket in VSCode in Jupyter notebooks in a dialect of Scheme closest to the book. This requires this declaration at the top of each Racket file:
Writing Racket (Scheme) in Jupyter Notebooks
First, we’re going to install Jupyter. As we don’t want to contaminate our global Python installation, we’ll do this in a venv
Debugging Python CLI Arguments in VSCode
Command Palette (CTRL+SHIFT+P): Debug: Add Configuration
Debugging Python Tests in VSCode
VSCode offers native test capabilities that are quite useful. Testing Python in Visual Studio Code
Suppressing Rich Tracebacks in Typer Apps
This must be applied to the configuration of the Typer object created for the CLI.
Uninstalling Poetry Completions for zsh
Here’s how to enable: https://python-poetry.org/docs/#enable-tab-completion-for-bash-fish-or-zsh
Ubuntu Snaps in WSL & zsh
What on earth are “ Snaps ”?
Running Google Chrome GUI in WSL
This was working for me a while ago but today, when I tried, it was not.
Comments are Failures in Coding
“The proper use of comments is to compensate for our failure to express ourselves in code.” — Robert C. Martin, Clean Code
Launching a Web App from Stream Deck
This is actually much more of a hassle than I’d have expected …