AI Agency & Interpretability Workshop

The workshop will take place at Carnegie Mellon University, under the auspices of the Institute for Complex Social Dynamics and the Center for Formal Epistemology, on the weekend of September 19th to 20th, 2026.

This interdisciplinary meeting explores how formal methods from game and decision theory and the notions of agency and rationality from those contexts can help us to interpret, explain, and predict the behavior of frontier artificial intelligence. Sessions will cover open questions and novel results in AI agency and interpretability, belief elicitation, preference elicitation, and instrumental convergence.

Speakers

Speakers at the workshop will include:

  • Vincent Conitzer (Computer Science, Carnegie Mellon University)
  • Daniel Herrmann (University of North Carolina, Chapel Hill) and Ben Levinstein (Antrhopic)
  • Aran Nayebi (Machine Learning, Carnegie Mellon University)
  • Bryan Wilder (Machine Learning, Carnegie Mellon University)
  • Aydin Mohseni (Philosophy, Carnegie Mellon University)

Dates & Times

Saturday, September 19th, 9:00am–5:00pm
Sunday, September 20th, 9:00am–5:00pm

Location

Baker Hall A53, Steinberg Auditorium, Carnegie Mellon University

Registration

Please join us! Attendance is free, but please register if you intend to attend.

Program