We ran Agent K against 12 seeded production incidents. It named the correct root cause 5 times out of...
Our incident-response agent got the root cause wrong 7 times out of 12. It still never made a bad rollback.
Related
Claude Code Cost Control in Production: Token Budgets, Caching Strategies, and What the Billing Dashboard Hides
Claude Code Cost Control in Production: Token Budgets, Caching Strategies, and What the...
I Planned 10 LLM Evaluation Experiments And Only Ran 1. It Was Enough.
I didn’t set out to write a benchmark paper. I wanted to answer a much dumber, much more practical...
Using Claude to decrypt Carmageddon
I used to play Carmageddon with @edulazaro and we decided to play it again now that the new one is...