Open Philanthropy recommended a grant of $100,000 to the UC Berkeley to support an AI red-teaming bootcamp in summer 2025, led by Professor Andrew Reddie at the Berkeley Risk and Security Lab. The bootcamp is aimed at postdocs and early career professionals from backgrounds other than machine learning; its goal is to give participants a better understanding of how AI systems work, how they fail, and how those failures can be detected.
This falls within Open Philanthropy’s focus area of potential risks from advanced artificial intelligence.