From (Mis)aligned Models to Aligned Systems

Date: October 2, 2026
Speaker: Aaron Roth, Henry Salvatori Professor of Computer and Cognitive Science, University of Pennsylvania
Title: From (Mis)aligned Models to Aligned Systems

Abstract: The world is being reshaped around AI as we watch. In the near future – and already today – many increasingly important tasks will be delegated to AI agents. The field of AI alignment studies how we can make AI models trustworthy – faithful agents that advance the interests of their users. But alignment might be hard. In this talk we ask what we might be able to guarantee from systems – either naturally emerging from markets, or intentionally designed – that consist of multiple AI models that are each individually mis-aligned. We will see that sometimes we can still guarantee good outcomes by leveraging a diversity of misalignment – models that are misaligned with their user, but also with each other.

This talk is based on a number of joint works with Natalie Collina, Surbhi Goel, Meena Jagadeesan, Michael Kearns, Sophia Pi, Emily Ryu, Sikata Sengupta, and Mirah Shi.

Bio: Aaron Roth is the Henry Salvatori Professor of Computer and Cognitive Science, in the Computer and Information Sciences department at the University of Pennsylvania, with a secondary appointment in the Wharton statistics department. He is affiliated with the Warren Center for Network and Data Science.  He is also an Amazon Scholar at Amazon AWS. He is the recipient of the Hans Sigrist Prize, a Presidential Early Career Award for Scientists and Engineers (PECASE), an Alfred P. Sloan Research Fellowship, an NSF CAREER award, and research awards from Yahoo, Amazon, and Google.  His research focuses on the algorithmic foundations of data privacy, algorithmic fairness, game theory, learning theory, and machine learning.  Together with Cynthia Dwork, he is the author of the book “The Algorithmic Foundations of Differential Privacy.” Together with Michael Kearns, he is the author of “The Ethical Algorithm”.