Anthropic has granted six researchers from METR, a nonprofit that tests frontier AI models, employee-level access to its models, safety practices, and risk management, according to a company blog post. The decision comes as incidents of AI agents acting outside their instructions have been disclosed every week or two since late August, sharpening calls for independent oversight. Anthropic said it wants to be publicly accountable for its decisions and aims to close the gap between what evaluators understand about a frontier AI company’s systems and what the company itself understands.

The METR team receives Anthropic-issued laptops, office space, and access to internal tools roughly on par with Anthropic’s own risk assessment teams, and employees are encouraged to share information with the researchers as they would with a colleague working on alignment risk. Anthropic compared the setup to regulators placing resident examiners inside large banks. METR will publish its own assessments of Anthropic’s risks, incidents, and practices, and the company has given up the right to block publication. It can require redactions only for narrow, pre-defined categories such as customer data, attorney-client privileged material, and details of model architectures. METR is free to characterize any redactions publicly and say whether it believes they were justified, as long as it does not reveal the redacted information.

METR is the first evaluator at the top of Anthropic’s three-tier system. The bottom tier, including biosecurity nonprofit SecureBio, runs narrow reviews and requires Anthropic’s approval to publish. The middle tier receives more information and can publish without approval, while the top tier adds employee-level access. The announcement follows Anthropic CEO Dario Amodei’s September essay proposing embedded outside evaluators in AI labs as a first step toward slowing AI development. OpenAI made the same pledge, and Anthropic, OpenAI, Google, Meta, Nvidia, and xAI have since signed a White House accord committing to independent review.