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 ...

METR (pronounced 'meter') is a research nonprofit that scientifically measures whether and when AI systems might threaten catastrophic harm to society.

An interactive chart of documented incidents in which AI agents deliberately acted against their users' intentions, scored along two axes: overreach and deception. Of these, 25 involve elements of ...

In February–April 2026, we ran a survey of 349 technical workers (including 87 software engineers, 71 researchers, 129 academics and PhD students, and 48 founders and managers) about their usage of AI ...

Understanding AI systems’ ability to automate AI research and development is important: it could enable recursive self-improvement where AI development outpaces society’s ability to adapt, and it’s a ...

AI developers and the public want to know whether AI agents would pursue very harmful actions, like unsanctioned cyberattacks. An alignment assessment would attempt to understand the worst misaligned ...

Future AI systems may be capable enough to carry out sabotage, either via malicious real-world actions or via intentionally tampering with evaluations. We want to track the sabotage capabilities of AI ...

Chairman Hawley, Ranking Member Kim, and members of the subcommittee, thank you for inviting me to testify today. My name is Chris Painter and I am the President of METR. It is a great honor to be ...

Legible reasoning already has well-established value in human contexts. Scientists are required to share their methods, federal judges to explain the legal reasoning behind case rulings, and engineers ...

AI agents are improving rapidly at autonomous software development and machine learning tasks, and, if recent trends hold, may match human researchers at challenging months-long research projects in ...

We’re releasing a new version of our time horizon estimates (TH1.1), using more tasks and a new eval infrastructure. Our estimates of time horizons for many models have been updated. The new estimates ...

METR previously published a paper which found the use of AI tools caused a 20% slowdown in completing tasks among experienced open-source developers, using data from February to June 2025. To ...