OpenAI opens internal models to Apollo, METR, Transluce and Goodfire for embedded safety assessments

fatihdin4en · x · 2026-11-17

OpenAI is partnering with Apollo Research, METR, Transluce, and Goodfire on "embedded assessments," giving outside experts deep access to internal models to investigate alignment and test safeguards. Goodfire will embed interpretability researchers to monitor and debug training runs; findings will be published as the collaboration progresses.

Related event: OpenAI Launches Embedded Assessments with Four External Safety Labs(19 posts)→

Original post →

More from Safety

Safety channel →