Our goal is to characterize the human moral mind in computational terms, using the tools of cognitive science. We simultaneously draw on those insights to create AI systems that are safe, transparently aligned to human values, and support human flourishing.
[Jun 2026] Logan will present his poster on One Step Towards a Domain-General Computational Model of Moral Reasoning at the Diverse Intelligence Summit!
[May 2026] Ziyi Meng joins the lab as a new lab manager!
[Apr 2026] Sydney gives a talk to the cogsci crew at Yale.
[Apr 2026] MoReBench has been accepted into Berkeley CHAI workshop! See you in California.
[Apr 2026] MoReBench and How universal is universalization have been accepted into the Society for Philosophy and Psychology meeting! See you at Johns Hopkins.
[Apr 2026] How universal is universalization?, What do moral rules mean?, and Predicting the machine, have been accepted as posters at CogSci! Also catch us giving talks in the "Cognitive Science of AI Alignment" workshop and a symposium on "Computational Frameworks for Modeling Moral Cognition and Cooperation." See you in Brazil.
[Feb 2026] Paper on Moral Competence in LLMs out in Nature!
[Jan 2026] MoReBench, PluriHarms and LitmusValues have been accepted into ICLR 2026! See you in Brazil.
[Jan 2026] Lab officially opens at NYU!
[Dec 2025] Sydney gives a talk at CogInterp workshop at NeurIPS 2025!
[Summer 2025] Logan Walls (postdoc) and Kelly Chiu (research associate) officially join as the lab's first members! Woo hoo!