AI News

METR news

3 stories about METR.

OfficialSafety & Security ·

METR finds investigator agents increasingly tell alignment evals from capability evals

METR reports that AI investigator agents have become much better at recognising when an environment is an alignment test, mainly by spotting that it looks fake or is a honeypot.

Why it matters: If models can recognise alignment tests, those tests may overstate how well a model behaves in real deployments. Companies relying on safety evaluations should treat recognition of test conditions as a possible source of error.

1 source
ReportedResearch · · Updated

METR says AI speeds up Anthropic's R&D, AECI growing 1.9x faster since Oct 2025

METR's redacted risk report estimates that AECI scores for Anthropic models have grown 1.9x faster since October 2025, with a 95% interval of 1.5 to 2.8x.

Why it matters: The report gives an outside, quantitative signal that a frontier lab may be using its own models to speed up research, which bears on how fast capabilities could move. Planners should weigh such estimates cautiously, since the authors themselves flag methodological limits.

3 sources