General Physics Colloquium, Professor Lionel Levine, Math Department, Cornell University

Title:  The Math and Physics of AI Safety

Host:  Veit Elser

Abstract:  AI holds great promise and, many believe, great peril. How can physicists and mathematicians contribute to ensuring that promise is fulfilled, and peril avoided? What types of artificial minds (if any) should humanity aspire to build? I'll highlight some research directions in the nascent field of AI safety. This talk will be interactive, and I'll mostly supply questions rather than answers, so please come prepared to debate!