2023 Machine Learning Laboratory Public Lecture with Scott Aaronson

AI Safety

Abstract: Thoughts about AI safety, shaped by a year's leave at OpenAI to work on the intersection of AI safety and theoretical computer science.  I'll discuss what I've worked on, including a scheme for watermarking the outputs of Large Language Models such as GPT, as well as proposals such as cryptographic backdoors and a theory of AI acceleration risk.

Bio: Scott Aaronson is a theoretical computer scientist and David J. Bruton Jr. Centennial Professor of Computer Science at the University of Texas at Austin. His primary area of research is theoretical computer science, and his research interests center around the capabilities and limits of quantum computers, and computational complexity theory more generally. Prior to coming to UT, Scott Aaronson taught for nine years in Electrical Engineering and Computer Science at MIT.