My personal agent can now answer with a small web page, drawn in a sandboxed frame inside the chat bubble. Getting a game to show up was easy. Keeping it safe, on-theme, and running when the next message arrived was the actual work.

A one-way ratchet on code size stopped my agent-written codebase growing. Clamping it exactly onto the tree turned out to be the mistake, and the fix is three hundred lines of deliberate slack.

An orchestrator that talks to a human and dispatches long-running workers has an IO problem that is harder than its scheduling problem. Every design mistake I can point at turned out to be an IO mistake.

Two things make agents ship quickly — a work board a human can actually verify, and a gate cheap enough that everybody runs it. Both turned out to be the same problem, and it is a design problem rather than a discipline problem.

A taxonomy of every self-edit an autonomous agent made over seven weeks, with a pie chart, and the one category that ever made the codebase smaller.

Two replies to my agent carried the same facts. One got a thumbs up, one got a thumbs down, and the difference wasn't accuracy — it was whether the verdict survived contact with the reader.

I measured what formatting costs an LLM agent. A quarter of every long reply is pipes and dashes, generated one token at a time while someone waits.

Four mistakes from building a self-evolving agent, and the one measurement that would have caught all of them.

Hand-typing code is becoming the slow part of software. I think the job moves to design, review and the gates you set for agents — and here is the best evidence against that.

Version one put a language model in the reply path to format replies. Version two deleted it and wrote a parser. Here is what each one actually cost.