AI News

OpenAI Collaborates with GoodfireAI on Interpretability Research

OpenAIUpdated Nov 17 00:13

AI summary

OpenAI announced that GoodfireAI will station interpretability researchers to use its platform to analyze the internal structure of OpenAI models. The related work focuses on training process monitoring, debugging, and alignment, helping OpenAI researchers discover and improve safety. This is part of the embedded evaluation jointly conducted by OpenAI with ApolloResearch, METR_Evals, TransluceAI, and GoodfireAI.

Body

@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.

Source

OpenAI