Posts
2 posts
Notes from driving AI coding agents through large native codebases. Every claim ships with its artefact — the spec, the diff, the commit, the test output. The failures are the interesting part.
All Posts
499 out of 500, on purpose
The CPU passes every SingleStepTests instruction but one. The one it fails, it fails deliberately.
Starting the scoreboard at zero
Why I am building a Game Boy emulator in C++ with AI agents, and publishing every number.