[Translate to Englisch:] Flyer mit Bild von Yoshua Bengio

Talk by Yoshua Bengio "Obtaining Safety Guarantees to avoid AI Catastrophic Risks"


On May 7, 2024, the Faculty of Computer Science, together with the research network Data Science, hosted a lecture by the world-renowned computer scientist Yoshua Bengio. As a Turing Award winner and one of the so-called "Godfathers of AI", he is one of the leading scientists that promote a responsible development of AI techniques.

The lecture was part of the celebration of 20 years of the Faculty of Computer Science at the University of Vienna and 50 years of teaching computer science at the University of Vienna. The Faculty of Computer Science is delighted by the strong interest in the lecture. In the fully packed BIG Hörsaal lecture hall in the main building of the University of Vienna, Yoshua Bengio held his lecture and subsequently engaged in discussions with the participants.


» Stream of the lecture

» Photo gallery



Title: Obtaining Safety Guarantees to avoid AI Catastrophic Risks

Abstract: This presentation will start by providing context regarding catastrophic scenarios from future advanced AI systems, both in terms of dangerous misuse (threatening democracy and national security) and loss of control to superhuman AI systems. This will clarify the need to address both the technical alignment challenge and the political challenge of coordination and governance, at national and international levels. In particular, I 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. I 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).

Bio: Yoshua Bengio is Full Professor in the Department of Computer Science and Operations Research at Université de Montreal, as well as the Founder and Scientific Director of Mila and the Scientific Director of IVADO. He also holds a Canada CIFAR AI Chair.

Considered one of the world’s leaders in artificial intelligence and deep learning, he is the recipient of the 2018 A.M. Turing Award with Geoff Hinton and Yann LeCun, known as the Nobel prize of computing. He is a Fellow of both the Royal Society of London and Canada, an Officer of the Order of Canada, Knight of the Legion of Honor of France and member of the UN’s Scientific Advisory Board for Independent Advice on Breakthroughs in Science and Technology.


Further Reading

» Turing Award winner Yoshua Bengio

» "Statement on AI Risk" signed by Yoshua Bengio


Press articles (in German)

» Experte warnt vor Erstarken von "Schurken-KIs" und fordert "Plan B" [Beitrag APA Science]

» Experte warnt vor Erstarken von "Schurken-KIs" und fordert "Plan B" [Beitrag derStandard.at]

» Forscher warnt vor Gefahren Künstlicher Intelligenz [Beitrag Ö1 Mittagsjournal]

» Pionier warnt vor Gefahren künstlicher Intelligenz [Beitrag science.orf.at]

» Droht Kontrollverlust? Turing-Preisträger Bengio warnt vor „Schurken-KIs“ [Beitrag krone.at]


Interview with Yoshua Bengio (in English)

» How to avoid AI Catastrophic Risks [Beitrag Rudolphina]