Note: I am spending 2026-27 at Goodfire, working full-time on the science of interpretability.

  • Editor, Philosophical Logic
  • Editor, Open Mind

    • Publications

    Some representative publications include:

  • Resource Rationality: Foundations of Cognitive Economy, MIT Press (forthcoming, preprint here).
  • Why be Random?, Mind.
  • Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability, with A. Geiger et al., Journal of Machine Learning Research.
  • Probing the Quantitative-Qualitative Divide in Probabilistic Reasoning, with D. Ibeling, K. Mierzewski, and M. Mossé, Annals of Pure and Applied Logic.
  • A Topological Perspective on Causal Inference, with D. Ibeling, Proc. NeurIPS.
  • Inference from Explanation, with L. Kirfel and T. Gerstenberg, Journal of Experimental Psychology: General.
  • Normality and Actual Causal Strength, with J. Kominsky and J. Knobe, Cognition.
  • Calibrating Generative Models: The Probabilistic Chomsky-Schützenberger Hierarchy, Journal of Mathematical Psychology.

    • See here for a longer list of papers.

    Teaching & Advising

    I have been unreasonably fortunate to work with truly amazing students. Some recent/current Ph.D. students:

  • Krzysztof Mierzewski (Philosophy, 2020)
  • Declan Thompson (Philosophy & Symbolic Systems, 2023)
  • Cristina Ceballos (Law & Philosophy, 2023)
  • Duligur Ibeling (Computer Science, 2024)
  • Atticus Geiger (Linguistics, 2024)
  • David Gottlieb (Philosophy & Symbolic Systems)
  • Jacqueline Harding (Philosophy & Symbolic Systems)
  • Bendix Kemmann (Philosophy & Symbolic Systems)

    • And M.S. students in Symbolic Systems:

  • Brendan Fleig-Goldstein
  • Dirk Hofland
  • Ethan Herenstein
  • Jack Beasley
  • Kara Schechtman
  • Junyi Tao
  • Puyin Li