Skip to content
TechCrunch AI· Aditya Mehta·Indexed by this site · Originally publishedSelectedAttention42

Anthropic grants employee-level access to METR researchers

Anthropic is letting METR researchers look under the hood with employee-level access

AI summary

Anthropic announced in a blog post that it granted employee-level access to six researchers from METR to independently evaluate Anthropic's models, safety practices, and risk management. The METR team received Anthropic-issued company laptops, office space, and internal tools roughly on par with the company's risk assessment team. Employees are encouraged to share information with them as they would with colleagues working on alignment risks. METR will independently publish its assessments of Anthropic's risks, incidents, and practices. Anthropic cannot veto publication but may request redactions for pre-defined narrow categories such as customer data, attorney-client privileged information, or model architecture information. METR can publicly state whether these redactions are reasonable. This is the highest tier in the three-tier evaluator system Anthropic is building; lower-tier evaluators such as the biosecurity nonprofit SecureBio require Anthropic approval to publish.

Why it was selected

Anthropic granted METR employee-level access and waived the right to veto publication; this tiered arrangement of evaluator permissions provides a reference for other labs introducing external evaluators.

Read originaltechcrunch.com