Raphaël Millière
@raphaelmilliere.com
📤 6667
📥 945
📝 134
Philosopher of Artificial Intelligence & Cognitive Science
https://raphaelmilliere.com/
pinned post!
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
5 months ago
4
52
6
reposted by
Raphaël Millière
Department of Statistics
3 months ago
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
0
3
3
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!
3 months ago
3
48
0
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
3 months ago
5
141
43
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
loading . . .
Transformers
https://oecs.mit.edu/pub/ppxhxe2b
4 months ago
1
53
14
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...
loading . . .
Associationist Theories of Thought (Stanford Encyclopedia of Philosophy)
https://plato.stanford.edu/entries/associationist-thought/
4 months ago
1
39
9
reposted by
Raphaël Millière
Sam Gershman
4 months ago
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.
5
187
26
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
5 months ago
4
52
6
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
loading . . .
How Do Transformers Learn Variable Binding in Symbolic Programs?
YouTube video by Raphaël Millière
https://youtu.be/Ux8iNcXNEhw
5 months ago
1
52
9
reposted by
Raphaël Millière
Andrew Perfors
9 months ago
Ah... the morning Australian ritual, waking up and checking into Bluesky with the thought "what fresh hell happened overnight while I was asleep?"
4
31
1
I'm mildly amused by the fact that when you watch obscure videos on syntactic theory, Youtube will serve you ads for Gammarly
9 months ago
0
10
0
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...
loading . . .
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...
https://simons.berkeley.edu/workshops/llms-cognitive-science-linguistics-neuroscience
9 months ago
1
19
0
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!
10 months ago
1
22
0
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.
11 months ago
1
20
3
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...
loading . . .
Schmidt Sciences to Award $12 Million to Advance Research on Beneficial AI
AI2050 fellowships recognize scholars working to create AI for a better world
https://www.schmidtsciences.org/schmidt-sciences-to-award-12-million-to-advance-research-on-beneficial-ai/
11 months ago
3
40
0
reposted by
Raphaël Millière
Mike Frank
11 months ago
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...
add a skeleton here at some point
2
137
63
reposted by
Raphaël Millière
Clément Canonne
12 months ago
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
9
53
5
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:...
add a skeleton here at some point
12 months ago
2
49
16
Happy to see Bluesky taking off. Here's an attempt at a Philosophy of AI starter pack:
go.bsky.app/8pf4odt
add a skeleton here at some point
12 months ago
13
61
14
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?
add a skeleton here at some point
12 months ago
1
7
0
reposted by
Raphaël Millière
Tomer Ullman
12 months ago
reinforcement learning
1
48
11
PSA: If you're on Bluesky and Mastodon (or another fediverse network), you can bridge the two with this tool:
fed.brid.gy
loading . . .
Bridgy Fed
https://fed.brid.gy/
12 months ago
1
10
3
reposted by
Raphaël Millière
Clément Canonne
about 1 year ago
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!
loading . . .
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...
https://usyd.wd3.myworkdayjobs.com/en-US/USYD_EXTERNAL_CAREER_SITE/job/Multiple-Continuing--Tenure-Track--Academic-Positions--School-of-Computer-Science--The-University-of-Sydney_0124838-1
1
21
17
reposted by
Raphaël Millière
Melanie Mitchell
about 1 year ago
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...
loading . . .
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.
https://santafe.edu/about/jobs/postdoc-ai-modeling
0
15
17
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
loading . . .
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 ...
https://philpapers.org/rec/MILIMF-2
about 1 year ago
3
16
4
reposted by
Raphaël Millière
Edouard Machery
about 1 year ago
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
loading . . .
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 ...
https://philpapers.org/rec/SHECAT-11
1
39
10
📄I finally preprinted this new chapter for the upcoming Oxford Handbook of the Philosophy of Linguistics, edited by the excellent Gabe Dupre, Ryan Nefdt & Kate Stanton. Before you get mad about the title – read on! 1/
arxiv.org/abs/2408.07144
loading . . .
Language Models as Models of Language
This chapter critically examines the potential contributions of modern language models to theoretical linguistics. Despite their focus on engineering goals, these models' ability to acquire...
https://arxiv.org/abs/2408.07144
about 1 year ago
1
36
19
New paper (in open access): "Philosophy of cognitive science in the age of deep learning" – in which I argue that although progress in DL is largely driven by engineering goals, it is far from irrelevant to (the philosophy of) cog sci, and vice versa.
wires.onlinelibrary.wiley.com/doi/10.1002/...
loading . . .
Philosophy of cognitive science in the age of deep learning
Cognitive science has a key role to play in the rigorous evaluation of deep learning models, through behavioral methods inspired by cognitive psychology as well as intervention methods inspired by ne....
https://wires.onlinelibrary.wiley.com/doi/10.1002/wcs.1684
over 1 year ago
0
10
3
I look forward to speaking at the 12th Annual Marshall M. Weinberg Symposium @UMich on Friday, alongside researchers whose work I deeply admire – Yejin Choi,
@melaniemitchell.bsky.social
, and Paul Smolensky. More information including link to the livestream:
lsa.umich.edu/weinberginst...
over 1 year ago
0
5
1
In this new piece for the Institute of Art and Ideas, I examine the messy state of model evaluation in AI research and argue that we need to adopt best practices from cognitive science & supplement behavioral tests with interventions. Read here:
iai.tv/articles/the...
loading . . .
The Turing Tests of today are mistaken
<p><em>Companies like OpenAI try to show that AIs are intelligent by hyping their high scores in behavioural tests – an approach with roots in the Turing Test. But there are hard limits to what we can...
https://iai.tv/articles/the-turing-tests-of-today-are-mistaken-auid-2790?_auid=2020
over 1 year ago
1
10
1
reposted by
Raphaël Millière
Max Grafe
over 1 year ago
Stop the presses, this thing musicologists and composers have been saying for literal decades just got validated by one of the fields of study people actually respect
loading . . .
Pythagoras was wrong: There are no universal musical harmonies, study finds
The tone and tuning of musical instruments has the power to manipulate our appreciation of harmony, new research shows. The findings challenge centuries of Western music theory and encourage greater e...
https://phys.org/news/2024-02-pythagoras-wrong-universal-musical-harmonies.html?fbclid=IwAR0yIeWYtdgmnvPqulLH65CgzzERLHMj7ttcKb4Waj-hjo5K1GXKJ-xnpCg
7
174
62
OpenAI unveiled its video generation model Sora two weeks ago. The technical report emphatically suggests that video generation models like Sora are world simulators. Are they? What does that even mean? I'm taking a deep dive into these questions in a new blog post (link below).
over 1 year ago
1
12
2
reposted by
Raphaël Millière
Ida Momennejad
over 1 year ago
📣📣Delighted to share our paper with amazing team Safoora Yousefi, Leo Betthauser, Hosein Hasanbeig,
@raphaelmilliere.com
on neuro-inspired analysis of LLMs, LLama2 70B & Vicuna 13B. Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in LLMs
arxiv.org/abs/2310.00313
🧵1/n
1
9
2
There's a lot of speculation about whether OpenAI's video generation model Sora has a 'physics engine' (bolstered by OAI's own claims about 'world simulation'). Like the debate about world models in LLMs, this question is both genuinely interesting and somewhat ill-defined. 🧵1/
over 1 year ago
3
27
6
📄Now preprinted – Part I of a two-part philosophical introduction to language models co-authored with
@cameronbuckner.bsky.social
! This first paper offers a primer on language models and an opinionated survey of their relevance to classic philosophical issues. 1/5
arxiv.org/abs/2401.03910
loading . . .
A Philosophical Introduction to Language Models -- Part I:...
Large language models like GPT-4 have achieved remarkable proficiency in a broad spectrum of language-based tasks, some of which are traditionally associated with hallmarks of human intelligence....
http://arxiv.org/abs/2401.03910
almost 2 years ago
2
32
17
reposted by
Raphaël Millière
Cameron Buckner
almost 2 years ago
Dear Philosophy of ML folks, as you transition from holidays to Syllabus Scramble Season: Raphael Milliere and I will soon arXiv a paper "A Philosophical Introduction to Language Models", if you are looking for a reading on language models/transformers...
1
30
5
reposted by
Raphaël Millière
Cameron Buckner
almost 2 years ago
#booklaunch
day! Surrounded by family, friends, and colleagues who want to understand AI, but struggle to put the last ten years of furious progress into a systematic, philosophically-grounded framework? I have the perfect stocking-stuffer for you!
global.oup.com/academic/pro...
6
57
19
In this new Vox piece written with Charles Rathkopf, we ask why people – experts included – are so polarized about the kinds of psychological capacities they ascribe to language models like ChatGPT, and how we can move beyond simple dichotomies in this debate.
loading . . .
Why it’s important to remember that AI isn’t human
ChatGPT can talk like a person. You shouldn’t think of it as one.
https://www.vox.com/future-perfect/23971093/artificial-intelligence-chatgpt-language-mind-understanding
almost 2 years ago
1
16
6
📄 New preprint - The Alignment Problem in Context With the US Executive Order and the UK AI Safety Summit, AI safety concerns have taken the center stage in the past few weeks – But how concerned should we be in light of current developments? 🧵 1/
loading . . .
The Alignment Problem in Context
A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the...
https://arxiv.org/abs/2311.02147
about 2 years ago
1
6
1
you reached the end!!
feeds!
log in