AI Agency & Interpretability: A Workshop at Carnegie Mellon University

Speakers: Daniel Herrmann (Philosophy, UNC Chapel Hill) Ben Levinstein (Anthropic) Vincent Conitzer (Computer Science, CMU) Bryan Wilder (Machine Learning, CMU) Aran Nayebi (Machine Learning, CMU) Sven Neth (Philosophy, Pittsburgh) and Aydin Mohseni (Philosophy, CMU) Each talk runs forty minutes and is followed by forty minutes of discussion. Saturday 9 a.m. to 5 p.m. Sunday 9 a.m. to 3:30 p.m. Light breakfast from 8:30 and lunch both days. Sunday afternoon closes with lightning talks by Ida Mattsson, Damini Kusum, Dorian Clay, Daniel Kopp, and Boden Moraski, followed by a final panel discussion. Attendance is free and in person only, but please register if you plan to attend. Supported by the Center for Formal Epistemology, the Center for Conceptual Research on the Foundations of Safe AI, and the Institute for Complex Social Dynamics.