Raphaël Millière: The Vector Grounding Problem and Self-Consciousness
Raphaël Millière: The Vector Grounding Problem and Self-Consciousness
On self-consciousness, sentience claims about AI, and grounding in LLMs.
Appears in this episode
In episode 84 of The Gradient Podcast, Daniel Bashir speaks to Professor Raphaël Millière.
Professor Millière is a Lecturer (Assistant Professor) in the Philosophy of Artificial Intelligence at Macquarie University in Sydney, Australia. Previously, he was the 2020 Robert A. Burt Presidential Scholar in Society and Neuroscience in Columbia University’s Center for Science and Society, and completed his DPhil in philosophy at the University of Oxford, where he focused on self-consciousness.
Have suggestions for future podcast guests (or other feedback)? Let us know here or reach us at editor@thegradient.pub
Subscribe to The Gradient Podcast: Apple Podcasts | Spotify | Pocket Casts | RSS
Follow The Gradient on Twitter
Outline:
(00:00) Intro
(02:20) Prof. Millière’s background
(08:07) AI + philosophy questions and the human side / empiricism
(18:38) Putting aside metaphysical issues
(20:28) Prof. Millière’s work on self-consciousness, does consciousness constitutively involve self-consciousness?
(32:05) Relationship to recent pronouncements about AI sentience
(41:54) Chatbots’ self-presentation as having a “self”
(51:05) Intro to grounding and related concepts
(1:00:06) The different types of grounding
(1:08:48) Lexical representations and things in the world, distributional hypothesis, concepts in LLMs
(1:21:40) Representational content and overcoming the vector grounding problem
(1:32:01) Causal-informational relations and teleology
(1:43:45) Levels of grounding, extralinguistic aspects of meaning
(1:52:12) Future problems and ongoing projects
(2:04:05) Outro
Links:
Research
Raphaël Millière: The Vector Grounding Problem and Self-Consciousness
This interview is incredible. I have been studying referentiality for over 20 years now and this lecture connected a lot of dots. I love the resurgence of realism in the context of linguistic and cognitive scientific analysis of LLMs. Can you interview someone who can explore the process of vector representation of words? I want to know a lot more about that. So cool. Keep doing the good work.
I would love a follow up episode that goes into some of the questions you both touched on towards the end. There's a whole series you could don with Prof. Millière.