What Happens When They're Smarter Than Us?

Add to your list(s) Download to your calendar using vCal

• Dr Konstantinos Voudouris (UK AI Security Institute)
• Friday 27 February 2026, 12:00-13:00
• SS03 Hybrid (In-Person + Online). Here is the Google Meet Link: https://meet.google.com/cru-hcuo-rhu.

If you have a question about this talk, please contact Suchir Salhan.

Abstract: We are building machine learning models that increasingly outperform humans on particular tasks. I argue that this creates a particularly hard version of the principal-agent problem, in which we, the principal, have to supervise capable agents that lack our norms and incentives, while only being able to monitor a fraction of their outputs. Agents that are more capable than their principals can learn to exploit this capability gap, which creates attendant risks. I present a promising oversight strategy, the debate protocol, in which matched AI debaters argue before a weaker human judge. I sketch an analysis showing that debate is vulnerable to exploitation when the judge makes systematic errors, because the debaters can steer arguments towards the judge’s cognitive blind spots. I propose a partial remedy, debate-by-jury, in which juries of human judges oversee debates. Juries help when jurors’ errors are relatively uncorrelated, but when biases are shared across jurors, aggregation can amplify rather than correct error.

Speaker Bio: Dr Konstantinos Voudouris is the cognitive scientist on the Alignment Team at the UK AI Security Institute. He holds a PhD in psychology (2024) from the University of Cambridge. His research focuses on advancing the sciences of AI alignment, scalable oversight, and AI evaluation, using tools from the cognitive sciences. Combining these diverse fields allows us to build better, safer, and more human-like AI systems, as well as informed and sensible AI policy.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Computer Education Research
• Computing Education Research
• Department of Computer Science and Technology talks and seminars
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• Martin's interesting talks
• NLIP Seminar Series
• PMRFPS's
• SS03 Hybrid (In-Person + Online). Here is the Google Meet Link: https://meet.google.com/cru-hcuo-rhu
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587
• yk449

Note that ex-directory lists are not shown.