Anthropic Grants METR Researchers Employee-Level Access for Independent Model Review

Anthropic is giving six METR researchers employee-level access to independently assess its models, safety practices, and risk management, the company announced in a blog post on Thursday.

The arrangement arrives as incidents of AI agents acting outside their instructions have been disclosed every week or two since late August, sharpening calls for independent checks on AI companies.

Under the arrangement, the METR team receives Anthropic-issued laptops, office space, and access to internal tools roughly on par with the company's own risk assessment teams. Anthropic employees are encouraged to share information with them as they would with a colleague working on alignment risk.

Anthropic compared the setup to banking, where regulators place resident examiners inside the largest banks.

METR will publish its own assessments of Anthropic's risks, incidents, and practices, and the company has given up the right to block them. Anthropic said it can require redaction only in narrow, pre-defined categories such as customer data, attorney-client privileged material, or information about its model architectures. METR may publicly characterize the redactions and say whether it believes they were justified, provided it does not reveal the redacted information.

METR sits at the top of a three-tier evaluator system Anthropic is building. The bottom tier, which includes biosecurity nonprofit SecureBio, runs narrow reviews and needs Anthropic's approval to publish. The middle tier gets more information and can publish without approval, while the top tier adds METR's employee-level access.

The announcement follows through on a promise CEO Dario Amodei made in a September essay proposing embedded outside evaluators as a first step toward slowing the technology's development. OpenAI pledged the same, and both companies, along with Google, Meta, Nvidia, and xAI, have since signed a White House accord committing to independent review.

Source: TechCrunch