Anthropic open-sources its eval design and hillclimbing playbook: 78.6%→90.5% accuracy at 1/5 cost

AGI Hunt · wechat · 2026-09-30

Anthropic's Lance Martin published a long-form post on claude.dev on designing evals and hillclimbing against them without fooling yourself. The method ships in the official claude-api skill via two new commands: /claude-api:build-eval and /claude-api:hillclimb.

Related event: Anthropic Adds Automated Eval Building and Hillclimbing Commands to Claude Code(6 posts)→

Original post →

More from coding & agent

coding & agent channel →