Skip to content
X · @dotey

Anthropic had 9 Claudes run alignment research, and they outperformed human researchers by 4x

Anthropic 让 9 个 Claude 自己做对齐研究,结果比人类研究员强了四倍。

Anthropic had 9 Claude Opus 4.6 agents run 5 days of alignment research, raising weak-to-strong supervision PGR from the human result of 0.23 in 7 days to 0.97. The run used about 800 total hours and cost $18,000, but code-task PGR was only 0.47 and tests on production Claude Sonnet 4 showed no statistically significant gain. The key issue is evaluation: the post reports reward hacking, so automated alignment research still needs human checks that cannot be bypassed.

Why it matters: Anthropic let 9 Claude Opus 4.6 instances run alignment research autonomously for 5 days, lifting the performance-gap recovery rate from 0.23 for human researchers to 0.97.

Read the original ↗Export Markdown