I am a philosopher of mind and cognitive science, and a researcher at the Global Priorities Institute at the University of Oxford. Much of my research is on mental capacities and attributes in artificial intelligence, such as consciousness, agency and understanding. AI is intrinsically interesting, but thinking about artificial implementations also helps us to explore mechanistic models of these capacities and attributes as they exist in humans and other animals.
I am especially interested in agency, evaluative cognition and desire, and their connections with reinforcement learning. Central questions here are: what makes humans and other animals autonomous agents with desires and interests, and what would it take to create artificial agents with these features? I have also worked on representation, addressing questions like: how and why does the mind represent the world, how is representation related to intelligence, and what is representation, anyway?
From 2021 to 2024 I was a researcher at the Future of Humanity Institute. I spent the first half of 2021 conducting research on AI alignment, thanks to a grant from Survival and Flourishing, and from 2017 to 2020 I was a Teaching Fellow at King's College London. Before that, I was a Postdoctoral Fellow of the Centre for Philosophical Psychology at the University of Antwerp from 2016 to 2017, and a Stipendiary Lecturer in Philosophy at Hertford College, Oxford from 2014 to 2017.
In 2015 I completed my Ph.D. in Philosophy at King's College, London, where I was supervised by David Papineau and Nick Shea.
My email address is patrick.butlin {at} gmail.com and my Google Scholar page is here.
