Projects in this stream will be on AI welfare and moral status; more specifically, on what it takes to be a moral patient and how we can determine whether AI systems meet the conditions. I'm looking for applicants who have ideas about these topics and are motivated to explore them in more detail.
This stream will allow fellows to collaborate on projects with me and other members of staff at Eleos. I will consider applicants for philosophical or empirical projects, and welcome project proposals from prospective fellows; you can make your application stand out by making a compelling and original proposal.
Research questions that would interest me include:
Philosophy: What would it take for an LLM persona, such as the assistant, to be a moral patient? Can non-conscious agents be moral patients? What are the functional requirements for valenced conscious experience? What is introspection, and what does it have to do with AI welfare?
Empirical: How can we extend recent research on the J-space to learn more about putative access consciousness in LLMs? Can we come up with new, useful ways to evaluate and monitor AI welfare?
Other: What can other disciplines teach us that is relevant to AI welfare? In particular, are there lessons from psychology or psychiatry that can help us understand how to build healthy AI minds?
Standard (1-2 hours of weekly 1:1s)
Indifferent
Weak preference
I am a philosopher of mind and a researcher at Eleos AI, where I work on AI consciousness, agency and welfare. Before joining Eleos, I worked at the Future of Humanity Institute and Global Priorities Institute in Oxford. I'm interested in projects including purely philosophical work on the grounds of moral status; research drawing on cognitive science to gain a mechanistic understanding of sentience and agency; and empirical studies that can shed light on welfare-relevant features in AI.
I am looking for fellows with the following characteristics:
I will talk through project ideas with scholars