METR
@METR_Evals
After Anthropic published their Sabotage Risk Report for Claude Opus 4.6, they shared an unredacted version with METR for us to review. We agree with their conclusion that catastrophic sabotage risk from Opus 4.6 is very low but not negligible, in light of the available evidence.
Anthropic@AnthropicAI · Feb 11When we released Claude Opus 4.5, we knew future models would be close to our AI Safety Level 4 threshold for autonomous AI R&D. We therefore committed to writing sabotage risk reports for future frontier models.
Today we’re delivering on that commitment for Claude Opus 4.6.
Open quoted post →Today we’re delivering on that commitment for Claude Opus 4.6.
5 385