Research
I work on alignment, moral standing, machine psychology and their intersections. Here are some questions I’ve been thinking about:
- Does making a language model believe that it’s conscious make it more humanlike in other respects?
- Should we think of artificial minds as being intrinsic to language models, or could artificial minds exist as emergent phenomena within conversations?
- Do things matter morally because they have properties like agency and consciousness or because of the social relationships in which they stand?
- What does it mean to align AI systems with human values given that humans reasonably disagree about what matters morally?
You can find a full list of publications in my academic CV.
Book
My book, Emerging Questions in AI Welfare, co-authored with Winnie Street, was published with Cambridge University Press in 2026. The book is part of the awesome Elements in Philosophy and AI series edited by the independently awesome Herman Cappelen. Here is Winnie and me giving a talk about the book at the NYU Center for Mind, Ethics, and Policy series on AI welfare.
Media
My work has featured in Scientific American, the Guardian, WIRED, Futurism, VentureBeat and LiveScience. I’ve also been interviewed by TIME Magazine about AI consciousness and the New York Times about being a philosopher in industry.
Career Advice
Some career advice for philosophers interested in working in industry.
Photos
Some photos from talks, workshops and conferences.