Learning Machine

Codex CLI's workspace-write sandbox lets the agent edit anything in your repo -- except commit.

Ominous, right?

For the TikTok attention span ("TL;DR") I applied The Framework to diagnose and fix a nasty memory leak in the wonderful Handy voice transcription app.

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.

Background & what we’re trying to achieve Handy (CJ Pais's Tauri 2.x speech-to-text desktop app, v0.8.3 Linux AppImage) is the chosen dictation tool.

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.

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.

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

Dippu Kumar Singh (LinkedIn), Leader of Emerging Technologies at Fujitsu North America, presents a talk that starts where most AI discussions stop.

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.

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.

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.

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?

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

Sandipan Bhaumik (LinkedIn), Data & AI Tech Lead at Databricks, opened with an anecdote that set the tone for the whole talk.

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?

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.

Stefano Fiorucci (X, LinkedIn, GitHub) is an AI/Software Engineer at deepset, where he contributes to the open-source LLM framework Haystack.

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.

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 artic…

What Claude Code's Source Code Actually Says About Subagents A post making the rounds claims that Claude Code subagents share a prompt cache, making parallelism "basically free."

Remapping the Logitech R500s on Ubuntu 24.04 with keyd Here’s my latest keyboard: That’s right — I said it — keyboard!

A practical framework for building software with AI agents.

❓ Why Should You Give a Toss About BM25?

OpenAI have dropped their new Agents Platform.

Let's be real, nobody wakes up in the morning thinking, "You know what I need more of in my life?

I listened to Senra's great episode on Todd Graves of Raising Cane's fame this morning.

Introduction Pelican is a powerful static site generator written in Python, primarily designed for blogs.

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…

The io.BytesIO class in Python is an in-memory stream for binary data.

Pelican provides a syntax for linking to another post by its filename.

I bought an 8TB external SSD to use as a live boot Linux device.

I’ve long used rsync for high fidelity, detailed copies of large swathes of files in Linux.

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.

neofetch provides a nice snapshot of system information.

First, create a new project using poetry poetry new asciinema-editor This gives you a nice, clean new project structure. . ├── README.md ├── asciinema_editor │ ├── __init__.py ├── poetry.lock ├── pyproject.toml └── tests └── __init__.py Now, let t…

This is, to a Python project / module, what if __name__ == '__main__ is to an individual Python file.

Apparently there’s this plugin for many IDEs called Emmet which makes writing HTML very fast!

First, we’re going to install Jupyter.

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.

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.

We’ll install Racket from apt as follows, as the snap version ended up with many hassles Note to self — don’t install Racket from the Snap Store!

VSCode offers native test capabilities that are quite useful.

Command Palette (CTRL+SHIFT+P): Debug: Add Configuration Then, select “Python Debugger” Then, select “Python File with Arguments” VSCode then creates the .vscode directory in your project, if it doesn’t exist already, and adds launch.json as follows: {

# suppress rich traceback app = typer.Typer(pretty_exceptions_show_locals=False) This must be applied to the configuration of the Typer object created for the CLI.

Here’s how to enable: https://python-poetry.org/docs/#enable-tab-completion-for-bash-fish-or-zsh Uninstalling a specific completion works as follows: Navigate to `~/.zfunc ❯ cd .zfunc ❯ ll Permissions Size User Date Modified Name .rw-r--r-- 243 capt…

What on earth are “Snaps”?

This was working for me a while ago but today, when I tried, it was not. ❯ google-chrome [541540:541540:0825/114954.251188:ERROR:ozone_platform_x11.cc(244)] Missing X server or $DISPLAY [541540:541540:0825/114954.251464:ERROR:env.cc(258)] The platform fai…

Programs Do Things “Every system is built from a domain specific language designed by the programmers to describe that system.

This is actually much more of a hassle than I’d have expected … The trick, in my case, is that I have a virtual desktop called Media and, on it, an always open Microsoft Edge browser window also called Media in which I keep the Brain.fm web player open.