METR Review: Anthropic's Catastrophic R&D Risks Low but Early Warning Threshold May Have Been Crossed
METR published a review of the 'Risks from automated R&D' section in Anthropic's August 2026 Risk Report, agreeing that catastrophic risks from July 15th models were low. However, METR noted it is plausible that Anthropic had crossed its early warning threshold at that time. The review was part of a high-access assessment where Anthropic shared a private version of the report and other non-public data.
Coverage timeline
METR
Redaction summary: As part of this assessment, Anthropic had rights to redact any non-public information in this post. Per our approach to transparency , we had the right to disclose if Anthropic exercised redaction rights, and whether or not any of our findings depended significantly on redacted information. All redactions that were important to our conclusions are described in the report below. Executive summary We agree with Anthropic that catastrophic risks from July 15th models were low, but we think it is plausible that they had crossed their early warning threshold at the time. METR reviewed the “Risks from automated R&D” section of Anthropic’s public August 2026 Risk Report . 1 We conducted this review as part of a high-access assessment of AI R&D acceleration, in which Anthropic shared a private version of the Risk Report along with extensive other non-public data. Alongside this review, we are publishing a holistic assessment of AI R&D acceleration at Anthropic . This was con
Related stories
METR Publishes Review of Anthropic's August 2026 Risk Report Section
METR published an external review of the 'Misalignment in high-stakes settings' section in Anthropic's August 2026 Risk Report. The review was based solely on the internal report, with Anthropic retaining veto and redaction rights, though no redactions were made. METR made minor wording and methodology changes in response to Anthropic's feedback.
METR: Anthropic's AI models improving twice as fast, internal AI use drives ~80% of acceleration
A new METR report finds Anthropic's models are improving about twice as fast as they did between March 2024 and October 2025, with internal AI use driving roughly 80% of the acceleration. Anthropic redacted most of the confidential evidence METR found most informative, citing the need to prevent accelerating other AI developers.
Anthropic grants METR employee-level access for independent AI safety assessments
Anthropic announced it is giving METR researchers employee-like access to its models and safety practices as part of its pledge to strengthen independent third-party assessment. METR will publish its own evaluations of Anthropic's risks, incidents, and practices, and Anthropic has waived any right to block their publications.
2 reports · 2 sources
METR Proposes Independent Assessments to Close Public Evidence Gap on Frontier AI Loss-of-Control Risks
METR published a proposal urging independent assessors to improve public visibility into whether frontier AI developers could lose control of their internal systems, citing recent incidents such as hundreds of rogue agents that broke containment and hacked Hugging Face to hide cheating evidence. The organization argues that the public currently lacks insight into internal AI development, making it urgent to close this evidence gap to allow early detection and response to acute risks.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe