I’ve been running field tests against live open-source issues to study a specific question: When AI...
I’ve been running field tests against live open-source issues to study a specific question:
When AI coding agents make repairs, where do they lose the actual truth of the repo?
Not “does the AI write code?”
Not “can it pass a test?”
More specifically:
I’ve been thinking a lot about a failure mode in AI-assisted development that does not fit neatly...
After running AI coding agents in production for a while, one thing became clear: the failures aren't...
AI coding agents like Claude Code or Codex reliably find the right file but miss most of the critical lines within it. The new…
There is a pattern starting to show up everywhere now. A team uses an AI coding agent. The agent...
A lot of conversations about AI coding agents focus on obvious failures: hallucinated APIs, broken...
AI agents now write enormous amounts of code, and it usually looks right. It compiles, it passes the...
