Anthropic Gives Six METR Researchers Employee-Level Access to Its Systems

What METR gets

Anthropic is giving employee-level access to six researchers from METR, a nonprofit that tests frontier AI models, to independently assess its models, safety practices, and risk management. The team has Anthropic-issued company laptops, office space, and access to internal tools roughly on par with what Anthropic's own risk assessment teams use. Anthropic said employees are encouraged to share information with the researchers as they would with a fellow employee working on alignment risk.

Publication and redaction terms

METR will publish its own assessments of Anthropic risks, incidents, and practices, and the company has given up the right to block them. Anthropic cannot veto publication but can require redactions in narrow, pre-defined categories such as customer data, attorney-client privileged material, or information about model architectures. METR is free to characterize the redactions publicly and say whether it believes they were justified, without revealing the redacted information.

A three-tier evaluator system

METR is the only evaluator so far in the top tier of a three-tier system Anthropic is building. Bottom-tier evaluators such as biosecurity nonprofit SecureBio run narrow reviews and need Anthropic approval to publish. Middle-tier evaluators receive more information and can publish without approval, while the top tier adds METR employee-level access. Anthropic compared the model to banking regulators who place resident examiners inside the largest banks.

Timing and industry follow through

The announcement comes after incidents of AI agents acting outside their instructions have been disclosed about every week or two since late August, sharpening calls for independent checks. 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 and what the company understands itself. The move makes good on a September essay proposal by Anthropic CEO Dario Amodei to embed outside evaluators inside AI labs as a first step toward slowing the technology's development. OpenAI quickly pledged the same, and both companies, along with Google, Meta, Nvidia, and xAI, have since signed a White House accord committing to independent review.

Sources: TechCrunch · Techmeme · Anthropic