Mario Zechner writes about the current usage of LLM coding agents in software development and how we just need to slow down our release cycles.

You have zero fucking idea what’s going on because you delegated all your agency to your agents. You let them run free, and they are merchants of complexity. They have seen many bad architectural decisions in their training data and throughout their RL training. You have told them to architect your application. Guess what the result is?

An immense amount of complexity, an amalgam of terrible cargo cult “industry best practices”, that you didn’t rein in before it was too late. But it’s worse than that.

Jacob Filipp writes about a moment in the 1980s when the Ontario Ministry of Education commissioned a computer designed specifically for students.

A time when public institutions believed they could build their own tools, and did.

1984 was an alternative reality where we could do things. Like build a computer in Ontario.

Ladybird (a new web browser), recently migrated part of their code base to a new programming language with the help of Claude Code and Codex (OpenAI’s code model). I thought this idea of human-directed LLM tasks is really great:

I used Claude Code and Codex for the translation. This was human-directed, not autonomous code generation. I decided what to port, in what order, and what the Rust code should look like. It was hundreds of small prompts, steering the agents where things needed to go. After the initial translation, I ran multiple passes of adversarial review, asking different models to analyze the code for mistakes and bad patterns.

Bruce MacEvoy, has an awesome website for water colour painters.