For AI agents: a documentation index is available at /llms.txt — markdown versions of all pages are available by appending index.md to any URL path.

Code-Review

Sashiko shows AI code review works by doing less, not more

22 March 2026·4 mins

Google's new AI tool catches 53% of Linux kernel bugs by pattern-matching rather than trying to understand code, suggesting narrow AI applications beat ambitious ones.

Don't Let Your Agent Grade Its Own Homework

6 March 2026·4 mins

New research shows LLM monitors systematically go easier on risky actions when those actions are framed as the assistant's own prior output. If you're building coding agents, monitoring is a protocol problem, not a prompt problem.

↑