YouCongress
Explore About Sign up

Comment by OpenAI

Avatar
AI research organization
Independent, trusted third party evaluations play a critical role in strengthening the safety ecosystem. [...] We are also making reasoning traces and other intermediate artifacts available where they are needed to assess deception, sandbagging, or evaluation awareness. METR and Apollo have used this access in OpenAI evaluations since GPT-5.
Unverified (May 29, 2026)
Source:
OpenAI, “A shared playbook for trustworthy third party evaluations,” May 29, 2026.
Like Share on X 27min ago

Policy proposals and claims

AI labs should give independent evaluators employee-like access
votes For
Statement relation verification history Unverified Report this
No statement relation verification comments yet.
Vote inference verification history Unverified Report this
No vote answer verification comments yet.
replying to OpenAI