Raphaël Millière
@raphaelmilliere.com
Philosopher of Artificial Intelligence & Cognitive Science
https://raphaelmilliere.com/
https://raphaelmilliere.com/
Pinned
Raphaël Millière
@raphaelmilliere.com
· Jun 10
Despite extensive safety training, LLMs remain vulnerable to “jailbreaking” through adversarial prompts. Why does this vulnerability persist? In a new paper published in Philosophical Studies, I argue this is because current alignment methods are fundamentally shallow. 🧵 1/13
Reposted by Raphaël Millière
With @jesusoxford.bsky.social we are looking for a Professor of Statistics.
Become part of a historic institution and a community focused on academic excellence, innovative thinking, and significant practical application.
About the role: tinyurl.com/b8uy6mr5
Deadline: 15 September
Become part of a historic institution and a community focused on academic excellence, innovative thinking, and significant practical application.
About the role: tinyurl.com/b8uy6mr5
Deadline: 15 September
August 26, 2025 at 1:36 PM
With @jesusoxford.bsky.social we are looking for a Professor of Statistics.
Become part of a historic institution and a community focused on academic excellence, innovative thinking, and significant practical application.
About the role: tinyurl.com/b8uy6mr5
Deadline: 15 September
Become part of a historic institution and a community focused on academic excellence, innovative thinking, and significant practical application.
About the role: tinyurl.com/b8uy6mr5
Deadline: 15 September
I'm happy to share that I'll be joining Oxford this fall as an associate professor, as well as a fellow of @jesusoxford.bsky.social and affiliate with the Institute for Ethics in AI. I'll also begin my AI2050 Fellowship from @schmidtsciences.bsky.social there. Looking forward to getting started!
August 21, 2025 at 2:08 PM
I'm happy to share that I'll be joining Oxford this fall as an associate professor, as well as a fellow of @jesusoxford.bsky.social and affiliate with the Institute for Ethics in AI. I'll also begin my AI2050 Fellowship from @schmidtsciences.bsky.social there. Looking forward to getting started!
Can LLMs reason by analogy like humans? We investigate this question in a new paper published in the Journal of Memory and Language (link below). This was a long-running but very rewarding project. Here are a few thoughts on our methodology and main findings. 1/9
August 11, 2025 at 8:02 AM
Can LLMs reason by analogy like humans? We investigate this question in a new paper published in the Journal of Memory and Language (link below). This was a long-running but very rewarding project. Here are a few thoughts on our methodology and main findings. 1/9
I wrote an entry on Transformers for the Open Encyclopedia of Cognitive Science (@oecs-bot.bsky.social). I had to work with a tight word limit, but I hope it's useful as a short introduction for students and researchers who don't work on machine learning:
oecs.mit.edu/pub/ppxhxe2b
oecs.mit.edu/pub/ppxhxe2b
Transformers
oecs.mit.edu
July 18, 2025 at 8:02 AM
I wrote an entry on Transformers for the Open Encyclopedia of Cognitive Science (@oecs-bot.bsky.social). I had to work with a tight word limit, but I hope it's useful as a short introduction for students and researchers who don't work on machine learning:
oecs.mit.edu/pub/ppxhxe2b
oecs.mit.edu/pub/ppxhxe2b
Happy to share this updated Stanford Encyclopedia of Philosophy entry on 'Associationist Theories of Thought' with
@ericman.bsky.social. Among other things, we included a new major section on reinforcement learning. Many thanks to Eric for bringing me on board!
plato.stanford.edu/entries/asso...
@ericman.bsky.social. Among other things, we included a new major section on reinforcement learning. Many thanks to Eric for bringing me on board!
plato.stanford.edu/entries/asso...
Associationist Theories of Thought (Stanford Encyclopedia of Philosophy)
plato.stanford.edu
July 14, 2025 at 7:31 AM
Happy to share this updated Stanford Encyclopedia of Philosophy entry on 'Associationist Theories of Thought' with
@ericman.bsky.social. Among other things, we included a new major section on reinforcement learning. Many thanks to Eric for bringing me on board!
plato.stanford.edu/entries/asso...
@ericman.bsky.social. Among other things, we included a new major section on reinforcement learning. Many thanks to Eric for bringing me on board!
plato.stanford.edu/entries/asso...
Reposted by Raphaël Millière
The sycophantic tone of ChatGPT always sounded familiar, and then I recognized where I'd heard it before: author response letters to reviewer comments.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
July 9, 2025 at 9:24 AM
The sycophantic tone of ChatGPT always sounded familiar, and then I recognized where I'd heard it before: author response letters to reviewer comments.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
"You're exactly right, that's a great point!"
"Thank you so much for this insight!"
Also how it always agrees even when it contradicts itself.
Despite extensive safety training, LLMs remain vulnerable to “jailbreaking” through adversarial prompts. Why does this vulnerability persist? In a new paper published in Philosophical Studies, I argue this is because current alignment methods are fundamentally shallow. 🧵 1/13
June 10, 2025 at 1:39 PM
Despite extensive safety training, LLMs remain vulnerable to “jailbreaking” through adversarial prompts. Why does this vulnerability persist? In a new paper published in Philosophical Studies, I argue this is because current alignment methods are fundamentally shallow. 🧵 1/13
Transformer-based neural networks achieve impressive performance on coding, math & reasoning tasks that require keeping track of variables and their values. But how can they do that without explicit memory?
📄 Our new ICML paper investigates this in a synthetic setting!
🎥 youtu.be/Ux8iNcXNEhw
🧵 1/13
📄 Our new ICML paper investigates this in a synthetic setting!
🎥 youtu.be/Ux8iNcXNEhw
🧵 1/13
How Do Transformers Learn Variable Binding in Symbolic Programs?
YouTube video by Raphaël Millière
youtu.be
June 3, 2025 at 1:19 PM
Transformer-based neural networks achieve impressive performance on coding, math & reasoning tasks that require keeping track of variables and their values. But how can they do that without explicit memory?
📄 Our new ICML paper investigates this in a synthetic setting!
🎥 youtu.be/Ux8iNcXNEhw
🧵 1/13
📄 Our new ICML paper investigates this in a synthetic setting!
🎥 youtu.be/Ux8iNcXNEhw
🧵 1/13
Reposted by Raphaël Millière
Ah... the morning Australian ritual, waking up and checking into Bluesky with the thought "what fresh hell happened overnight while I was asleep?"
February 12, 2025 at 8:27 PM
Ah... the morning Australian ritual, waking up and checking into Bluesky with the thought "what fresh hell happened overnight while I was asleep?"
I'm mildly amused by the fact that when you watch obscure videos on syntactic theory, Youtube will serve you ads for Gammarly
February 6, 2025 at 7:54 PM
I'm mildly amused by the fact that when you watch obscure videos on syntactic theory, Youtube will serve you ads for Gammarly
I'm back in the Bay Area for this great workshop at UC Berkeley – if you're in the area and interested in LLMs & Cog Sci, come along!
simons.berkeley.edu/workshops/ll...
simons.berkeley.edu/workshops/ll...
LLMs, Cognitive Science, Linguistics, and Neuroscience
At a conceptual level, LLMs profoundly change the landscape for theories of human language, of the brain and computation, and of the nature of human intelligence. In linguistics, they provide a new wa...
simons.berkeley.edu
February 3, 2025 at 3:04 AM
I'm back in the Bay Area for this great workshop at UC Berkeley – if you're in the area and interested in LLMs & Cog Sci, come along!
simons.berkeley.edu/workshops/ll...
simons.berkeley.edu/workshops/ll...
Losing Lynch is a strange feeling. This is hardly an original thing to say, but his work left a big impression on me since I was a teenager. I've rewatched most of his movies over the past year, they're every bit as enthralling as I remembered them. Now it's time to rewatch Twin Peaks!
a woman is sitting at a table with the words " one day the sadness will end "
ALT: a woman is sitting at a table with the words " one day the sadness will end "
media.tenor.com
January 17, 2025 at 2:04 AM
Losing Lynch is a strange feeling. This is hardly an original thing to say, but his work left a big impression on me since I was a teenager. I've rewatched most of his movies over the past year, they're every bit as enthralling as I remembered them. Now it's time to rewatch Twin Peaks!
My article 'Constitutive Self-Consciousness' is now published online in the Australasian Journal of Philosophy. It argues (spoiler alert!) against the claim that self-consciousness is constitutive of consciousness.
December 17, 2024 at 11:29 AM
My article 'Constitutive Self-Consciousness' is now published online in the Australasian Journal of Philosophy. It argues (spoiler alert!) against the claim that self-consciousness is constitutive of consciousness.
I'm happy to share that I'll be one of Schmidt Sciences's new AI2050 fellows! I'll be focusing on addressing the risk of interpretability illusions in AI – cases where interpretability methods yield seemingly plausible yet incorrect explanations.
www.schmidtsciences.org/schmidt-scie...
www.schmidtsciences.org/schmidt-scie...
Schmidt Sciences to Award $12 Million to Advance Research on Beneficial AI
AI2050 fellowships recognize scholars working to create AI for a better world
www.schmidtsciences.org
December 11, 2024 at 10:49 PM
I'm happy to share that I'll be one of Schmidt Sciences's new AI2050 fellows! I'll be focusing on addressing the risk of interpretability illusions in AI – cases where interpretability methods yield seemingly plausible yet incorrect explanations.
www.schmidtsciences.org/schmidt-scie...
www.schmidtsciences.org/schmidt-scie...
Reposted by Raphaël Millière
Three ManyBabies projects - big collaborative replications of infancy phenomena - wrapped up this year. The first paper came out this fall. I thought I'd take this chance to comment on what I make of the non-replication result. 🧵
bsky.app/profile/laur...
bsky.app/profile/laur...
The Manybabies4 paper is out! Infants' Social Evaluation of Helpers and Hinderers: A Large-Scale, Multi-Lab, Coordinated Replication Study onlinelibrary.wiley.com/doi/abs/10.1... 1000 babies tested in 37 labs; "Overall, 49.34% of infants preferred Helpers over Hinderers in the social condition"
Infants’ Social Evaluation of Helpers and Hinderers: A Large‐Scale, Multi‐Lab, Coordinated Replication Study
Evaluating whether someone's behavior is praiseworthy or blameworthy is a fundamental human trait. A seminal study by Hamlin and colleagues in 2007 suggested that the ability to form social evaluatio...
onlinelibrary.wiley.com
December 3, 2024 at 11:56 PM
Three ManyBabies projects - big collaborative replications of infancy phenomena - wrapped up this year. The first paper came out this fall. I thought I'd take this chance to comment on what I make of the non-replication result. 🧵
bsky.app/profile/laur...
bsky.app/profile/laur...
Reposted by Raphaël Millière
He's making a list,
He's checking it twice
He's gonna find out
Who's naughty or...
Searching in an unsorted list takes linear time, Christmas is postponed to January
He's checking it twice
He's gonna find out
Who's naughty or...
Searching in an unsorted list takes linear time, Christmas is postponed to January
November 28, 2024 at 7:46 AM
He's making a list,
He's checking it twice
He's gonna find out
Who's naughty or...
Searching in an unsorted list takes linear time, Christmas is postponed to January
He's checking it twice
He's gonna find out
Who's naughty or...
Searching in an unsorted list takes linear time, Christmas is postponed to January
Inspired by @mariaa.bsky.social's custom feed for NLP papers, I created a custom feed for philosophy papers posted on BlueSky. It's not perfect, but it works decently well:
bsky.app/profile/did:...
bsky.app/profile/did:...
November 25, 2024 at 11:52 AM
Inspired by @mariaa.bsky.social's custom feed for NLP papers, I created a custom feed for philosophy papers posted on BlueSky. It's not perfect, but it works decently well:
bsky.app/profile/did:...
bsky.app/profile/did:...
Happy to see Bluesky taking off. Here's an attempt at a Philosophy of AI starter pack:
go.bsky.app/8pf4odt
go.bsky.app/8pf4odt
November 23, 2024 at 11:13 AM
Happy to see Bluesky taking off. Here's an attempt at a Philosophy of AI starter pack:
go.bsky.app/8pf4odt
go.bsky.app/8pf4odt
I also persist in saying "computational resources" which almost feels old-fashioned. Though I believe that's what linguists call deverbal zero-nominalization and it's pretty common in English, so at some point it'll probably become part of the lexicon?
I know this ship has long sailed, but am I the only one to find the use of "compute" as a noun so off-putting?
November 23, 2024 at 5:55 AM
I also persist in saying "computational resources" which almost feels old-fashioned. Though I believe that's what linguists call deverbal zero-nominalization and it's pretty common in English, so at some point it'll probably become part of the lexicon?
Reposted by Raphaël Millière
reinforcement learning
November 15, 2024 at 1:25 PM
reinforcement learning
PSA: If you're on Bluesky and Mastodon (or another fediverse network), you can bridge the two with this tool: fed.brid.gy
Bridgy Fed
fed.brid.gy
November 15, 2024 at 2:02 AM
PSA: If you're on Bluesky and Mastodon (or another fediverse network), you can bridge the two with this tool: fed.brid.gy
Reposted by Raphaël Millière
ICYMI: The School of Computer Science at the University of Sydney 🇦🇺 is hiring, with multiple (equiv.) tenure-track positions. All areas of CS welcome, with a specific focus on Systems, PL, ML, and Quantum Computing.
usyd.wd3.myworkdayjobs.com/en-US/USYD_E...
Please share, and get in touch!
usyd.wd3.myworkdayjobs.com/en-US/USYD_E...
Please share, and get in touch!
Multiple Continuing (Tenure-Track) Academic Positions, School of Computer Science, The University of Sydney
Join a growing Faculty and be part of a University that places amongst the world’s best teaching and research institutions Located in the heart of Sydney’s bustling inner west quarter, close to beache...
usyd.wd3.myworkdayjobs.com
November 2, 2024 at 1:44 AM
ICYMI: The School of Computer Science at the University of Sydney 🇦🇺 is hiring, with multiple (equiv.) tenure-track positions. All areas of CS welcome, with a specific focus on Systems, PL, ML, and Quantum Computing.
usyd.wd3.myworkdayjobs.com/en-US/USYD_E...
Please share, and get in touch!
usyd.wd3.myworkdayjobs.com/en-US/USYD_E...
Please share, and get in touch!
Reposted by Raphaël Millière
Graduating PhDs and postdocs in AI, ML, Cogsci, or related areas: apply to work with me and others on AI models of visual and multimodal reasoning. Two years of funding with possible extension to a third year.
Application deadline November 22.
santafe.edu/about/jobs/p...
Application deadline November 22.
santafe.edu/about/jobs/p...
sfiscience
SFI seeksa full-time postdoctoral fellow to collaborate with Dr. Melanie Mitchell and other project participants in developing AI models of visual and multimodal reasoning.
santafe.edu
October 4, 2024 at 5:03 PM
Graduating PhDs and postdocs in AI, ML, Cogsci, or related areas: apply to work with me and others on AI models of visual and multimodal reasoning. Two years of funding with possible extension to a third year.
Application deadline November 22.
santafe.edu/about/jobs/p...
Application deadline November 22.
santafe.edu/about/jobs/p...
New chapter with
@cameronbuckner.bsky.social
on interventionist methods for interpreting deep neural networks. We review and discuss the significance of recent developments in interpretability research on DNNs from a philosophical perspective. 1/6
philpapers.org/rec/MILIMF-2
@cameronbuckner.bsky.social
on interventionist methods for interpreting deep neural networks. We review and discuss the significance of recent developments in interpretability research on DNNs from a philosophical perspective. 1/6
philpapers.org/rec/MILIMF-2
Raphaël Millière & Cameron Buckner, Interventionist Methods for Interpreting Deep Neural Networks - PhilPapers
Recent breakthroughs in artificial intelligence have primarily resulted from training deep neural networks (DNNs) with vast numbers of adjustable parameters on enormous datasets. Due to their complex ...
philpapers.org
October 3, 2024 at 2:37 AM
New chapter with
@cameronbuckner.bsky.social
on interventionist methods for interpreting deep neural networks. We review and discuss the significance of recent developments in interpretability research on DNNs from a philosophical perspective. 1/6
philpapers.org/rec/MILIMF-2
@cameronbuckner.bsky.social
on interventionist methods for interpreting deep neural networks. We review and discuss the significance of recent developments in interpretability research on DNNs from a philosophical perspective. 1/6
philpapers.org/rec/MILIMF-2
Reposted by Raphaël Millière
Nick Shea's terrific book on concepts is now out, and it is open access. Download it and read it!
philpapers.org/rec/SHECAT-11
philpapers.org/rec/SHECAT-11
Nicholas Shea, Concepts at the Interface - PhilPapers
Research on concepts has concentrated on the way people apply concepts online, when presented with a stimulus. Just as important, however, is the use of concepts offline, when planning what to ...
philpapers.org
September 10, 2024 at 2:36 AM
Nick Shea's terrific book on concepts is now out, and it is open access. Download it and read it!
philpapers.org/rec/SHECAT-11
philpapers.org/rec/SHECAT-11