Expression of Interest
We are interested in supporting research into, and collaborating with others on research relevant to Learning Theoretic AI Alignment, Agent Foundations, Singular Learning Theory, and related areas of mathematical research directed towards or relevant to AI safety. Future planned and possible projects include workshops, conferences, fellowships, and collaborations. We are hoping to ensure we are aware of ongoing research in relevant areas, and aware of people who are interested in contributing now and in the future. We are interested in people at all levels of seniority, and are happy to hear from graduate students, independent researchers, professors, research groups, university department contacts, and others who wish to be informed about future opportunities and programs.