leadership1 publisher
Anthropic broke an agent ceiling by making "is this design good?" a gradable question
A Labs engineer says prompt engineering and harness tuning both topped out on multi-hour builds, and the lever that moved them was a separate grading agent working from written criteria. The costs are named; the gain is not measured.
Publishers:anthropic.com
Reality
- Evidence42
- Adoption20
- Hype gap+18
- Incentives72
- Confidence55