University of Illinois Foundation — LLM Hacking Benchmarks

Visit Grantee Site

Table of Contents

Image courtesy of The Grainger College of Engineering

Open Philanthropy recommended a grant of $800,000 to the University of Illinois Foundation to support a project that will develop benchmarks to measure how well LLM agents perform hacking tasks, led by Daniel Kang.

This grant was funded via a request for proposals for projects benchmarking LLM agents on consequential real-world tasks. This falls within our focus area of potential risks from advanced artificial intelligence.