As AI systems grow increasingly powerful, what role could (or should?) mathematicians play in ensuring they remain safe and beneficial?
I will describe my path to AI safety research, and also discuss emerging research opportunities at the intersection of mathematics and AI safety. No machine learning background required.
Bio
Yevgeny is a math Professor at University of Toronto Mississauga. His interests lie at the intersection of Geometric Analysis, Quantitative Topology, Geometric Measure Theory, 3-manifold topology. Recently he has also been working on mathematical aspects of AI Safety.