I’m cofounded the Nottingham AI Safety Initiative (NAISI), a student society with faculty advisors and affiliation with UoN’s student union, for which I am currently helping to set up a research incubator whose governance and macrostrategy segment I’ll be managing. In this role I’ve taught courses on frontier AI governance, run multiple events on AI safety, and convinced several people to pursue careers in AI safety. Alongside NAISI I’m doing a part-time MA in policy research at Nottingham, focused on catastrophic AI risk.

My current main research is the infrastructure required for unmonitorable multi-agent collusion to become a reality, and what we can do about it. It grew out of my LessWrong work on encrypted agent communication.

I’ve also run BlueDot-informed AI governance courses, I help people move into AI safety careers from non-technical backgrounds, and I’ve written a front-paged article for LessWrong.

Check out my continually updated list of research questions: https://​​docs.google.com/​​document/​​d/​​1H4cUJQ8UoQmpNa5Gy9BJQ5ZrcCk7XPEFrbRqfViYoRE/​​edit?usp=sharing