In the last edition of We Should Do Something With AI, I discussed my Daily Doom experiment. How long can a coding agent build software before it all breaks down? I set up a system to autonomously build a Doom clone. Every night, the system would pick up the GitHub issues and add them to the game. If there were no issues, Claude would make something up. New features, new game mechanics. No humans involved. ...
Software experts must balance enthusiasm for generative AI’s genuine capabilities with critical scrutiny to prevent unchecked hype from driving poor technical decisions.
How to manage multiple Claude Code accounts across different machines using Jean-Claude to selectively sync configuration while keeping account-specific data separate.
As software development feedback loops accelerate toward minutes, quality assurance remains the final bottleneck where human judgment is still required.
Generating code is a solved problem. Codex, Claude Code, Mistral’s Vibe and Gemini CLI are all capable of creating good software. But writing code creates a form of entropy. The more we add to a system, the worse it gets. Claude, like a junior developer and their manager, couldn’t care less about refactoring and code quality. All three have no sense of the risk software entropy poses. Seasoned software engineers, on the other hand, are obsessed with refactoring to fight that entropy. ...
Open source will survive the rise of AI coding agents — it represents a creative human endeavor that AI tools themselves depend upon.
Coding agents have changed the way we build software. Most engineers still need to accept this reality, but the days of writing syntax are over. These days, we tell an agent which problem to solve. But while most of us are still coming to terms with this new reality, some of us are taking it further. Why work with one agent if you can spawn a legion? The silicon brains can handle hundreds of tasks simultaneously. Our carbon brain struggles with context switching and multitasking. ...
I truly dislike LLM-generated writing. The quality of the models’ output has vastly improved over the years, but the result stays the same. Writing is deeply human. Putting our thoughts on paper, with all the struggle and the rework, is how we learn. It’s how we get better as individuals and as a species. So, every autogenerated newsletter and LinkedIn reply feels like an affront to humanity. And it’s getting worse by the day. ...
A companion CLI for syncing your Claude Code configuration — CLAUDE.md, settings, hooks, and skills — across all your machines using Git.
4 AI agents build Hello World in Java with TDD, DDD, BDD and hexagonal architecture. The results are magnificent enterprise-grade atrocities.