- Who
- OpenAI
- What
- partners with GoodfireAI to embed interpretability researchers and analyze OpenAI models’ internals
- Quote
@GoodfireAI will embed interpretability researchers to use their platform to analyze our models’ internals.
Read next
See the full storyOpenAI Launches First Round of Embedded Assessments with Four External Research Groups@GoodfireAI will embed interpretability researchers to use their platform to analyze our models’ internals.
Their work focuses on training run monitoring, debugging, and alignment, helping our researchers identify and make safety improvements.
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.
