MEDIUMAi
Global
Anthropic Gives AI Safety Evaluators Insider Access
·Source: Bank Info Security
Updated:
Executive Summary
METR Researchers Gain Employee-Level Access to Assess Unreleased Models and Publish Independent Risk Findings Anthropic, one of the labs that pushed for embedded evaluators, said in a blog post that it is giving the indepe
Analysis
METR Researchers Gain Employee-Level Access to Assess Unreleased Models and Publish Independent Risk Findings Anthropic, one of the labs that pushed for embedded evaluators, said in a blog post that it is giving the independent evaluator Metr "employee-like access" to its models before deployment. This level of access is close to what Metr said are best practices for its assessors to understand how highly capable models behave.