Goodfire and OpenAI Collaborate on Embedded Evaluation
Goodfire announced an embedded evaluation with OpenAI to advance the safety and alignment of frontier models. Aditya Agarwal stated that the goal of their interpretability work is to make the methods reliable enough to be used on leading frontier models, and that this day has now arrived, emphasizing that this must be done right.
View original postWe’re announcing an embedded assessment with @OpenAI to advance safety and alignment at the frontier. https://t.co/WSZ43iSvZQ
View original
We’re announcing an embedded assessment with @OpenAI to advance safety and alignment at the frontier. https://t.co/WSZ43iSvZQ
Body
Our goal when starting an interpretability work was to develop confidence in our methods to the point where we could apply it to leading frontier models.
Really happy that day is here. This is super critical to get right.
AI Trends