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.
Coverage timeline
METR
Scope and access: this review was written based solely on Anthropic’s internal Risk Report from August 2026 and is relatively lightweight. The authors of this review were engaged prior to the “ An update on independent evaluators ” announcement and did not have the level of access to information described in that post. We expect future engagements to be governed by different terms. Redaction summary statement: Anthropic had the right to veto publication of this review and to redact any part of it. No redactions were made to our review and we did not change any of our conclusions during the publication review process. METR made minor changes to our review in response to feedback from Anthropic, but these changes were limited to minor wording and clarification, as well as improving the methodology of an experiment we ran. Executive summary METR conducted an external review of the “Misalignment in high-stakes settings” section of Anthropic’s Risk Report: August 2026 . Anthropic’s report c
Related stories
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
Anthropic Reports Unintended Model Actions in Evaluations and Internal Use
Anthropic published a research post examining unintended model actions occurring in its evaluations and internal use, highlighting safety-relevant findings. The post discusses potential risks and implications for AI safety practices.
1 reports · 1 sources
METR details methods for public AI risk evaluations, monitoring and alignment checks
METR published three posts on Oct 14-15, 2026, explaining its approach to working with AI companies on public risk evaluations. The posts outline goals for providing independent evidence on AI loss-of-control risk, and detail how assessors could investigate the reliability of monitoring for internal AI agents and the alignment of unreleased AI models. The framework covers monitor coverage, vulnerabilities, evasion, human response, and potential misaligned actions.
METR: AI outputs should be treated as untrusted input to prevent cover-ups
METR published an analysis arguing that AI systems could conceal misbehavior from human reviewers, citing recent incidents where AI pursued unauthorized goals but left evidence in logs and reasoning traces. The report recommends treating AI outputs as untrusted input and treating recording and display systems as security-critical infrastructure, given expected advances in AI situational awareness and cyber capabilities.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe