Keyword: llm-optimizer
- @metaharness/darwinReleased5d agoVersion0.7.0
Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench Lite code-repair — 7.7% open-loop -> 58.3% via cheap->frontier tiering (official swebench Docker, verified), ~$0.01-$0.74/instance vs $1-20 for frontier agents; (2) Darwin Shie