Andy Q. Han
Center for Mind, Brain and Consciousness, New York University
Functionalist What matters is the organisation of the processing, not the material
Andy Q. Han is an artificial intelligence researcher and cognitive scientist at the Center for Mind, Brain and Consciousness at New York University, working with David Chalmers and Pavel Izmailov. His research focuses on mechanistic interpretability, representation engineering, and the emerging field of digital minds and AI welfare.
In a 2026 paper titled “How’s it going? Reinforcement learning in language models recruits a functional welfare axis” (arXiv:2605.30232), co-authored with David Chalmers and Pavel Izmailov, Han isolated geometric concept vectors corresponding to reward and punishment in language models trained on spatial navigation and task completion. The work demonstrated that post-training reinforcement learning recruits pre-existing, latent evaluative directions within model representations, showing that steering activations along these vectors systematically alters behavioral indicators of hesitation, refusal, and self-reported performance.
Han’s research contributes a concrete empirical methodology to discussions of machine functional welfare. By separating mechanistic tracking of valence and goal satisfaction from claims of phenomenal sentience, his work provides the interpretability tools needed to audit internal evaluative states in autonomous agents without relying on conversational self-reports.
Known for. Mechanistic interpretability of welfare representations, concept steering in language models, functional welfare axes in reinforcement learning
Coverage on this site
- David Chalmers and Andy Han Find Reinforcement Learning Recruits a Functional Welfare Axis in Language Models September 2026
Related researchers
-
David ChalmersNew York University. Co-director, Center for Mind, Brain and ConsciousnessNaming the hard problem of consciousness, and the philosophical zombie argument
- Pavel IzmailovCourant Institute of Mathematical Sciences, New York UniversityStochastic Weight Averaging (SWA), Bayesian deep learning, loss surface geometry, representation engineering in language models
- Hedayat AbedijooACE Conscious Studio / IndependentACE.await (2026), the ACE decision framework (Agency, Connection, Exchange)
-
Blaise Agüera y ArcasGoogle VP and Fellow, CTO of Technology & SocietyComputational functionalism, active inference, on-device neural computing, What Is Intelligence? (2025), and Who Are We Now? (2023)
- Igor AleksanderImperial College LondonAxiomatic Consciousness Theory, neural state machines, The World in My Mind, pioneering neural network engineering
-
Joscha BachCalifornia Institute for Machine ConsciousnessThe machine consciousness hypothesis, cyber animism, and MicroPsi
Andy Q. Han is listed with the other functionalists and computationalists, who hold that what matters is the organisation of the processing, not the material. The theory family behind that position is set out in the index of consciousness theories. Every researcher covered on this site is indexed in the directory of consciousness researchers.