I work as research director at the Cooperative AI Foundation, and am also an affiliated at the Centre for the Governance of AI. Before that, I completed my DPhil in computer science at the University of Oxford.
My research concerns safety and cooperation in multi-agent systems, motivated by the problem of ensuring that AI and other powerful technologies are developed and governed safely and democratically.
Research Keywords
game theory; machine learning; A(G)I safety; causality; cooperative AI; verification; (multi-agent) reinforcement learning; mechanism design; computational complexity; AI governance; computational social choice
Other Keywords
art; (democratic) socialism; history; (experimental) (electronic) music; printmaking; philosophy; futurism; economics; film; Scandinavia; (vegan) cooking; nature; clubbing; mathematics; effective altruism; feminism







