Open Philanthropy recommended a grant of $1,922,145 over two years to Stanford University to support work on developing methods for measuring AI capabilities that are more robust than current techniques to factors such as style and scale. This research will be led by Professor Tatsunori Hashimoto.
This grant was funded via a request for proposals for projects related to improving LLM capability evaluations. This falls within Open Philanthropy’s focus area of potential risks from advanced artificial intelligence.