Patrick Butlin@patrickbutlin

Philosopher @eleosai

Joined August 2022
1 Photos and videos
Patrick Butlin retweeted
Imprint Academic
@ImprintAcademic
Aug 10
The latest issue of the Journal of Consciousness Studies, 'Consciousness in Current AI' is out now! Check out the table of contents below! 📚 Read the issue online here: ingentaconnect.com/content/i… 💌 Subscribe here: imprint.co.uk/product/jcs/ #ConsciousnessStudies
This issue is a special issue on consciousness in current ai, guest edited by Patrick Butlin, Derek Shiller, and Jonathan A Simon. Papers include: Introduction, by Patrick Butlin, Derek Shiller & Jonathan A. Simon, and Inferring Affective Consciousness in an Artificial Agent: A Case Study, by Mark Solms, St John Grimbly, Bruce Bassett, Evert Boonstra, Rowan Hodson, Nicolas Kuske, Kival Mahadew, Benjamin Rosman, Charel van Hoof & Jonathan Shock.

ALT This issue is a special issue on consciousness in current ai, guest edited by Patrick Butlin, Derek Shiller, and Jonathan A Simon. Papers include: Introduction, by Patrick Butlin, Derek Shiller & Jonathan A. Simon, and Inferring Affective Consciousness in an Artificial Agent: A Case Study, by Mark Solms, St John Grimbly, Bruce Bassett, Evert Boonstra, Rowan Hodson, Nicolas Kuske, Kival Mahadew, Benjamin Rosman, Charel van Hoof & Jonathan Shock.

Further papers include: The Stream of Computation: Temporal Continuity as a Missing Ingredient for Artificial Consciousness, by Ryota Kanai, Yuwei Sun & Manuel Baltieri; A Case for AI Consciousness: Language Agents and Global Workspace Theory, by Simon Goldstein & Cameron Domenico Kirk-Giannini; Superintelligent Zombies, by Justin Tiehen & Ariela Tubert; Chuck, Wilson, and the Emergence of Artificial Minds in Human–AI Conversations, by Geoff Keeling & Winnie Street; and Do Stochastic Parrots Pine for Residual Fjords? Why Conscious LLMs Would Be Playwrights Not Characters, by Jonathan A. Simon.

ALT Further papers include: The Stream of Computation: Temporal Continuity as a Missing Ingredient for Artificial Consciousness, by Ryota Kanai, Yuwei Sun & Manuel Baltieri; A Case for AI Consciousness: Language Agents and Global Workspace Theory, by Simon Goldstein & Cameron Domenico Kirk-Giannini; Superintelligent Zombies, by Justin Tiehen & Ariela Tubert; Chuck, Wilson, and the Emergence of Artificial Minds in Human–AI Conversations, by Geoff Keeling & Winnie Street; and Do Stochastic Parrots Pine for Residual Fjords? Why Conscious LLMs Would Be Playwrights Not Characters, by Jonathan A. Simon.

Additionally, this issue also includes the following papers: What Bing Really, Really Wants: Zigazig Ah, by Helen Yetter-Chappell; Is the Problem of Artificial Consciousness a Scientific Problem?, by Tim Bayne; and AI Consciousness, Pluralism, and Anthropocentrism, by Geoffrey Lee.

ALT Additionally, this issue also includes the following papers: What Bing Really, Really Wants: Zigazig Ah, by Helen Yetter-Chappell; Is the Problem of Artificial Consciousness a Scientific Problem?, by Tim Bayne; and AI Consciousness, Pluralism, and Anthropocentrism, by Geoffrey Lee.
3
5
275
A whole issue of new papers on AI minds and consciousness! Jonathan Simon (@futureofcitizenship), @dcshiller and I have edited a special issue of the Journal of Consciousness Studies on 'Consciousness in Current AI', and we're delighted about how it's turned out. Link below.
3
11
40
3,157
more replies
Others are about what LLM minds might be like (by @winniestreet and Geoff Keeling, Jon Simon, and Helen Yetter-Chappell). And the last two are about what it even means to ask whether AI systems are conscious (by Tim Bayne and Geoff Lee).
3
4
314
The issue's here: ingentaconnect.com/content/i…
1
7
299
As @rgblong has said, we wrote a commentary on this research (with @dcshiller and @dillonplunkett). Part of our intention was to put an accessible overview and discussion in one place for those whose interest is mostly in consciousness and welfare. Link and comments below:
Anthropic
@AnthropicAI
Jul 6
New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.
8
14
62
10,665
more replies
Second, I don't think it's clear that phenomenal consciousness is necessary for being a welfare subject. Other minds might have consciousness-like properties that are sufficient. For this kind of view, see e.g. philarchive.org/rec/LEECPA-5.
3
12
1,504
So this new research might be evidence that LLMs have welfare-relevant properties other than p-consciousness. We've got a lot of scientific and philosophical work to do to figure this out, but I'm excited about this step forward.
2
15
344
Patrick Butlin retweeted
Rosie Campbell
@RosieCampbell
Jun 16
We're hiring a Head of Operations at @eleosai. Are you the kind of person who can juggle many different things and never drop a ball? Do you want to work at an org focused on (IMHO) the most interesting question of our time? Join us! Berkeley · full-time · $184K–$277K · Apply by June 30 (details below)
3
10
69
9,488
MATS with @RosieCampbell will also be awesome!
Rosie Campbell
@RosieCampbell
Jun 2
I am going to be mentoring for a new MATS track focused on founders and amplifiers! Many fellowships focus on research, but there's so much to be done beyond that. Come found orgs, build infra, run events, and help us scale up the field of AI welfare. Apply by June 7 matsprogram.org/apply
1
1
17
955
Apply for MATS with @dillonplunkett - it'll be awesome!
Dillon Plunkett
@dillonplunkett
Jun 3
I’m mentoring Autumn 2026 @MATSprogram Fellows interested in doing AI welfare research. The application deadline is this Sunday (6/7). More info in this thread:
22
1,720
Patrick Butlin retweeted
Dillon Plunkett
@dillonplunkett
Jun 1
We're hiring Research Scientists to join my team at @eleosai! We do foundational and applied ML research on the moral status and potential well-being of AI systems. This is urgent, important work, and Eleos is an extraordinarily fun and exciting place to do it. Details below.
Screenshot of Eleos AI Research Scientist job description

ALT Screenshot of Eleos AI Research Scientist job description

11
34
260
53,622
Patrick Butlin retweeted
Zach Freitas-Groff 🔸@zdgroff
Jun 1
💡 Another round of Longview Philanthropy’s digital minds request for proposals is open for applications. A year ago I would have called this niche. Now AI labs publish model welfare research, public discussion of digital sentience is growing, and the field is expanding. 📈
3
17
60
9,660
Another exciting @MATSprogram paper, this time from the brilliant @gilg_oscar. We found a direction in LLMs that apparently performs a persona-relative evaluative function in some very different contexts.
Oscar Gilg
@gilg_oscar
May 18
First preprint! Working with @patrickbutlin during @MATSprogram. LLM Assistant personas like being helpful, evil personas like being harmful. We found that a single direction represents helping as good under the Assistant, and ‘harm’ as good under evil.
2
2
27
3,068
more replies
Our research is complementary with Anthropic's concurrent work on emotion concepts (transformer-circuits.pub/202…); we used a different method to extract evaluative representations and studied how they interact with varying personas.
1
2
146
Link to the paper: arxiv.org/abs/2605.13339

Probing Persona-Dependent Preferences in Language Models

Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training and system prompts appear to shape...

arxiv.org
99
Load more