METR strikes deal for independent investigation of Anthropic agent incidents, Redwood joins
ajeya_cotra · x · 2026-09-12
Evals organization METR announced an agreement with Anthropic to conduct an independent investigation of the company's agent incidents and its models' alignment properties, and will publish one or more public reports describing findings and terms of engagement.
Alignment research org Redwood Research confirmed several of its staff have been subcontracted by METR for the investigation, calling independent investigation crucial for managing misalignment risk.
It is the first concrete independent investigation to materialize following the third-party evaluation commitments in Dario Amodei's "pacing" essay.
Related event: METR to Independently Investigate Anthropic's Agent Incidents and Alignment(4 posts)→
More from Safety
- Bing separates AI training from AI search grounding with new site controls — OnlineInference · 2026-10-31
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- Forethought: US has 9x China's AI compute, can afford to pace the frontier — willmacaskill · 2026-10-31
- unpromptedconf takeaways: security programs face forced change as reachable vulnerabilities can't be risk-accepted — scottleibrand · 2026-10-31
- Reachable vulnerabilities can't be risk-accepted away, unpromptedconf speaker argues — scottleibrand · 2026-10-31
- AI safety researchers argue labs' silence on x-risk is a large-scale ethical mistake — DavidSKrueger · 2026-10-31