- Who
- OpenAI
- What
- launched its first round of embedded assessments
What happened
OpenAI is working with Apollo Research, METR Evals, Transluce AI, and Goodfire AI on embedded assessments that give outside experts deep access to its internal models and systems. The experts will investigate alignment and test safeguards as part of OpenAI’s ongoing alignment and safety research.
Read next
See the full storyOpenAI Launches First Round of Embedded Assessments with Four External Research GroupsReported by 3 sources
We’re working with @ApolloResearch, @METR_Evals, @TransluceAI, and @GoodfireAI on embedded assessments: giving outside experts deep access to our internal models and systems to investigate alignment and test our safeguards.
These assessments build on our ongoing alignment and safety research, bringing independent scrutiny to how we identify and manage risks in our systems.
The story so far
OpenAI has launched its first round of embedded assessments, giving four external research groups—Apollo Research, METR Evals, Transluce AI, and GoodfireAI—deep access to its internal models and systems to investigate alignment and test safeguards, according to OpenAI and co-founder Greg Brockman. In a pilot, OpenAI will host six Apollo Research safety evaluators to examine whether models covertly work against developers' intentions or undermine their own or successor models' alignment and control mechanisms, OpenAI and Apollo said. Apollo said it will receive relevant training code, datasets, reinforcement-learning rollouts, and intermediate checkpoints, but its access to staff and information is limited to agreed claims, specific models, and time periods. OpenAI also reserves the right to withhold information for technical infeasibility, security risks, or IP protection, and while Apollo can publish independent conclusions, OpenAI may limit the public evidence supporting them. GoodfireAI will embed interpretability researchers to use its platform to analyze OpenAI's model internals, OpenAI said. The company stated that GoodfireAI's work focuses on training run monitoring, debugging, and alignment to help OpenAI researchers identify and make safety improvements.
