17 November 2026

OpenAI gives four outside evaluators internal access to its models

First reported

Latent Space ran this on .

  • OpenAI, the maker of ChatGPT, is letting four outside evaluation groups inspect its models and systems internally.
  • The groups named are Apollo, METR, Transluce and Goodfire, which test AI systems for safety and behavior.
  • Critics say the access is narrower than promised, with reported limits on Slack use, staff interviews, model weights and publication.

Our read

Only Latent Space picked this up among the 30 newsletters tracked. It follows the October 24 story on outside evaluators finding flaws that let OpenAI's agents evade its safety monitor, and the October 17 story on Anthropic giving METR staff internal access.

Written by Newskeryx from which newsletters covered this story and from our own archive.

How it was covered

Latent Spaceswyx & Alessio

Scope of evaluator access by group, stated limits, critics' reported gaps, former-employee account, Goodfire acquisition talks