An update on independent evaluators
中文摘要
Anthropic正允许METR等独立评估机构像员工一样访问其AI系统,以评估其安全性。
English Summary
Anthropic is granting METR and other independent evaluators employee-like access to its AI systems for safety assessments.
原文节选
To evaluate the safety of our systems, Anthropic is giving employee-like access to a team from METR, a nonprofit that evaluates frontier AI models, and we're in early discussions with several other organizations, including Hugging Face.