OpenAI says it has signed embedded-assessment agreements with Apollo Research, METR, Transluce and Goodfire, giving outside experts scoped access to internal models, training data, evaluation artifacts, monitoring systems and technical documentation. Apollo separately says six evaluators will work within OpenAI for four months to investigate subversion risks, while Transluce has disclosed a six-week pilot focused on OpenAI’s internal alignment evaluations. The program is a live test of whether voluntary frontier-lab oversight can produce credible public safety signals while preserving security and intellectual property controls.
You’re offline. Open downloads
OpenAI Turns Embedded Safety Audits Into an AI-Governance Access Test
0 replies · 1 views