METR finds low sabotage risk in Claude Opus 4 and 4.1 after independent review
METR reviewed unredacted evidence and agreed that catastrophic sabotage risk from Claude Opus 4 and 4.1 was low, while warning that reasoning-hiding and evaluation-awareness claims were overconfident. Anthropic said the review led it to revise threat models and alignment practices, including training changes for reasoning monitorability.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
Independent access to nonpublic evidence, concrete review findings, and documented changes to Anthropic's threat models and monitoring-oriented training directly strengthen controls against autonomous sabotage.
Assessment history
- R1Away 40 · confidence 84
New October 2025 independent risk review with verified operational effects on Anthropic's sabotage assessment and alignment practices.
14 Aug 2026