My name is Jeanne Salle, I’m a first-year PhD student in the AI Safety and Alignment group at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems, advised by Maksym Andriushchenko and Sahar Abdelnabi. Before that, I participated in the MATS program in Berkeley and London. I’m interested in doing research on better understanding and mitigating risks from increasingly capable AI systems.

I discovered AI safety during my Master’s and volunteered at the Centre pour la Sécurité de l’IA, a French think-tank dedicated to informing policymakers about AI risks. I organized events and weekly discussion groups, taught the AI safety course in ENS Ulm and contributed to the AI Safety Atlas (a textbook distilling AI safety research). I’m now facilitating the AI Safety, Ethics & Society’s course.

I’m interested in anything AI safety-related: technical research, AI governance, regulations, forecasting/futures studies, how to communicate about risks, etc. Recently, I’ve also enjoyed studying geopolitics and philosophy.

Feel free to reach out at jeanne.salle@yahoo.fr! I’m always happy to chat :)