Abstract:

This presentation will start by providing context for avoiding catastrophic outcomes from future advanced AI systems, in particular on the need to address both the technical alignment challenge and the political challenge of coordination, at national and international levels. In particular, Prof. Bengio will discuss the proposal of a multilateral network of publicly funded non-profit AI labs to work on alignment and preparing for the eventual emergence of rogue AIs, presented in my Journal of Democracy paper. They will then outline a machine learning research program to obtain quantitative and conservative risk evaluations to address the alignment challenge. This is based on amortized inference of Bayesian posterior over causal theories of the data available to the AI, using generative AI to approximate that posterior and mathematical methods developed recently around generative flow networks (GFlowNets).

Sign up here to attend in-person: https://forms.gle/jskeGfsoziiWLnzC7
Sign up here to attend virtually: https://forms.gle/V4c2DJfCQRBH73io8