Showing 1–7 of 7 · #reliability

Nov 03AGENTSAI agent failure modes: a field guide and postmortem template7 min ↗Nov 02TESTSLLM temperature explained: what actually changes from 0 to 1.57 min ↗Oct 15PROMPTSThe "red-team yourself" prompt: self-critique that works, and when it backfires6 min ↗Oct 11AGENTSTool-use evals are broken. Here's how to fix them.6 min ↗Sep 29TESTSStructured outputs vs. plain prompts: when constrained decoding is worth it6 min ↗Sep 25AGENTSStep budgets and stopping rules for AI agents6 min ↗Jul 14AGENTSEvaluating AI agents end to end6 min ↗