Taylor Webb
@taylorwwebb.bsky.social
Studying cognition in humans and machines https://scholar.google.com/citations?user=WCmrJoQAAAAJ&hl=en
Pinned
Taylor Webb
@taylorwwebb.bsky.social
· Mar 10
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
Many recent studies have found evidence for emergent reasoning capabilities in large language models, but debate persists concerning the robustness of these capabilities, and the extent to which they ...
arxiv.org
LLMs have shown impressive performance in some reasoning tasks, but what internal mechanisms do they use to solve these tasks? In a new preprint, we find evidence that abstract reasoning in LLMs depends on an emergent form of symbol processing arxiv.org/abs/2502.20332 (1/N)
This was a blast! Thanks for joining us!
Was a pleasure to discuss the cognitive basis of reasoning at an @ivado.bsky.social workshop with legends like @alisongopnik.bsky.social @lauraruis.bsky.social @taylorwwebb.bsky.social and Andrew Granville!
January 31, 2026 at 11:49 PM
This was a blast! Thanks for joining us!
Reposted by Taylor Webb
What should academics be doing right now?
I have been writing up some thoughts on what the research says about effective action, and what universities specifically can do.
davidbau.github.io/poetsandnurs...
It's on GitHub. Suggestions and pull requests welcome.
github.com/davidbau/poe...
I have been writing up some thoughts on what the research says about effective action, and what universities specifically can do.
davidbau.github.io/poetsandnurs...
It's on GitHub. Suggestions and pull requests welcome.
github.com/davidbau/poe...
January 26, 2026 at 3:27 AM
What should academics be doing right now?
I have been writing up some thoughts on what the research says about effective action, and what universities specifically can do.
davidbau.github.io/poetsandnurs...
It's on GitHub. Suggestions and pull requests welcome.
github.com/davidbau/poe...
I have been writing up some thoughts on what the research says about effective action, and what universities specifically can do.
davidbau.github.io/poetsandnurs...
It's on GitHub. Suggestions and pull requests welcome.
github.com/davidbau/poe...
Reposted by Taylor Webb
Can you solve this algebra puzzle? 🧩
cb=c, ac=b, ab=?
A small transformer can learn to solve problems like this!
And since the letters don't have inherent meaning, this lets us study how context alone imparts meaning. Here's what we found:🧵⬇️
cb=c, ac=b, ab=?
A small transformer can learn to solve problems like this!
And since the letters don't have inherent meaning, this lets us study how context alone imparts meaning. Here's what we found:🧵⬇️
January 22, 2026 at 4:09 PM
Can you solve this algebra puzzle? 🧩
cb=c, ac=b, ab=?
A small transformer can learn to solve problems like this!
And since the letters don't have inherent meaning, this lets us study how context alone imparts meaning. Here's what we found:🧵⬇️
cb=c, ac=b, ab=?
A small transformer can learn to solve problems like this!
And since the letters don't have inherent meaning, this lets us study how context alone imparts meaning. Here's what we found:🧵⬇️
Reposted by Taylor Webb
Come join us for this first worshop of a three part series on the computational ingredients of reasoning in minds and AI. Reasoning is a complex term, especially in light of an exploding category of methods in LLMs. These workshops will explore reasoning’s multiple facets.
IVADO unveils the schedule of the first workshop "Cognitive Basis of #Reasoning (in Minds and #AI)", Jan 27-29, 2026, spearheaded by @taylorwwebb.bsky.social and Dhanya Sridhar.
🗓️ Schedule and speakers: ivado.ca/en/events/co...
📥 Registration: event.fourwaves.com/thematicseme...
🗓️ Schedule and speakers: ivado.ca/en/events/co...
📥 Registration: event.fourwaves.com/thematicseme...
Cognitive Basis of Reasoning (in Minds and AI) | IVADO
ivado.ca
January 20, 2026 at 10:34 PM
Come join us for this first worshop of a three part series on the computational ingredients of reasoning in minds and AI. Reasoning is a complex term, especially in light of an exploding category of methods in LLMs. These workshops will explore reasoning’s multiple facets.
Another great commentary on recent claims that conjunctive codes obviate the need for binding. The binding problem is alive and well, for both ANNs and the brain.
Now out in @cp-trendscognsci.bsky.social: our short response to @neurosteven.bsky.social & Edward de Haan's recent paper on the binding problem. We argue that the binding problem arises because of tradeoffs faced by any information processing system, including the brain and DNNs. shorturl.at/RGXzt
January 16, 2026 at 4:03 PM
Another great commentary on recent claims that conjunctive codes obviate the need for binding. The binding problem is alive and well, for both ANNs and the brain.
We’ve now posted the schedule for our first workshop (Jan 27-29) ivado.ca/en/events/co...
January 16, 2026 at 1:51 PM
We’ve now posted the schedule for our first workshop (Jan 27-29) ivado.ca/en/events/co...
Reposted by Taylor Webb
Now out in @cp-trendscognsci.bsky.social: our short response to @neurosteven.bsky.social & Edward de Haan's recent paper on the binding problem. We argue that the binding problem arises because of tradeoffs faced by any information processing system, including the brain and DNNs. shorturl.at/RGXzt
January 16, 2026 at 10:38 AM
Now out in @cp-trendscognsci.bsky.social: our short response to @neurosteven.bsky.social & Edward de Haan's recent paper on the binding problem. We argue that the binding problem arises because of tradeoffs faced by any information processing system, including the brain and DNNs. shorturl.at/RGXzt
Reposted by Taylor Webb
Very much looking forward to this series of workshops on the computational ingredients of reasoning. We have an amazing lineup of speakers from diverse backgrounds, and there will be lots of opportunities for discussion. Please consider attending!
🧠 Computational Ingredients of Reasoning: participate in the next #IVADO Thematic Semester, which will be held in Montreal from January to March 2026.
➡️ Register now: event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
➡️ Register now: event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
December 17, 2025 at 11:09 PM
Very much looking forward to this series of workshops on the computational ingredients of reasoning. We have an amazing lineup of speakers from diverse backgrounds, and there will be lots of opportunities for discussion. Please consider attending!
Reposted by Taylor Webb
IVADO unveils the schedule of the first workshop "Cognitive Basis of #Reasoning (in Minds and #AI)", Jan 27-29, 2026, spearheaded by @taylorwwebb.bsky.social and Dhanya Sridhar.
🗓️ Schedule and speakers: ivado.ca/en/events/co...
📥 Registration: event.fourwaves.com/thematicseme...
🗓️ Schedule and speakers: ivado.ca/en/events/co...
📥 Registration: event.fourwaves.com/thematicseme...
Cognitive Basis of Reasoning (in Minds and AI) | IVADO
ivado.ca
January 15, 2026 at 4:09 PM
IVADO unveils the schedule of the first workshop "Cognitive Basis of #Reasoning (in Minds and #AI)", Jan 27-29, 2026, spearheaded by @taylorwwebb.bsky.social and Dhanya Sridhar.
🗓️ Schedule and speakers: ivado.ca/en/events/co...
📥 Registration: event.fourwaves.com/thematicseme...
🗓️ Schedule and speakers: ivado.ca/en/events/co...
📥 Registration: event.fourwaves.com/thematicseme...
Reposted by Taylor Webb
Excited to share our NEWEST PREPRINT led by @rochellekaper.bsky.social!!
osf.io/preprints/ps...
We ask: How do people learn multiple layers of environmental structure – w/o feedback – & how well do they *know* they’ve learned? Turns out, stimulus familiarity matters more than we thought! 🧵👇
osf.io/preprints/ps...
We ask: How do people learn multiple layers of environmental structure – w/o feedback – & how well do they *know* they’ve learned? Turns out, stimulus familiarity matters more than we thought! 🧵👇
OSF
osf.io
January 15, 2026 at 2:48 AM
Excited to share our NEWEST PREPRINT led by @rochellekaper.bsky.social!!
osf.io/preprints/ps...
We ask: How do people learn multiple layers of environmental structure – w/o feedback – & how well do they *know* they’ve learned? Turns out, stimulus familiarity matters more than we thought! 🧵👇
osf.io/preprints/ps...
We ask: How do people learn multiple layers of environmental structure – w/o feedback – & how well do they *know* they’ve learned? Turns out, stimulus familiarity matters more than we thought! 🧵👇
Reposted by Taylor Webb
When are impossibility proofs misleading? In infinitefaculty.substack.com/p/be-wary-of..., I discuss a common issue I see: proofs that are logically valid, but where the underlying assumptions are unjustified. I discuss ‘proofs’ that cognition cannot be tractably learned, and that LMs are 1/
Be wary of assumptions in impossibility arguments
A proof is only as good as its assumptions
infinitefaculty.substack.com
January 13, 2026 at 3:33 PM
When are impossibility proofs misleading? In infinitefaculty.substack.com/p/be-wary-of..., I discuss a common issue I see: proofs that are logically valid, but where the underlying assumptions are unjustified. I discuss ‘proofs’ that cognition cannot be tractably learned, and that LMs are 1/
Reposted by Taylor Webb
When and why do modular representations emerge in neural networks?
@stefanofusi.bsky.social and I posted a preprint answering this question last year, and now it has been extensively revised, refocused, and generalized. Read more here: doi.org/10.1101/2024... (1/7)
@stefanofusi.bsky.social and I posted a preprint answering this question last year, and now it has been extensively revised, refocused, and generalized. Read more here: doi.org/10.1101/2024... (1/7)
January 9, 2026 at 7:06 PM
When and why do modular representations emerge in neural networks?
@stefanofusi.bsky.social and I posted a preprint answering this question last year, and now it has been extensively revised, refocused, and generalized. Read more here: doi.org/10.1101/2024... (1/7)
@stefanofusi.bsky.social and I posted a preprint answering this question last year, and now it has been extensively revised, refocused, and generalized. Read more here: doi.org/10.1101/2024... (1/7)
Reposted by Taylor Webb
once again being driven insane by ML conference submissions
January 9, 2026 at 2:07 PM
once again being driven insane by ML conference submissions
Very much looking forward to this series of workshops on the computational ingredients of reasoning. We have an amazing lineup of speakers from diverse backgrounds, and there will be lots of opportunities for discussion. Please consider attending!
🧠 Computational Ingredients of Reasoning: participate in the next #IVADO Thematic Semester, which will be held in Montreal from January to March 2026.
➡️ Register now: event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
➡️ Register now: event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
December 17, 2025 at 11:09 PM
Very much looking forward to this series of workshops on the computational ingredients of reasoning. We have an amazing lineup of speakers from diverse backgrounds, and there will be lots of opportunities for discussion. Please consider attending!
Reposted by Taylor Webb
🧠 Ingrédients computationnels du raisonnement : participez au prochain semestre thématique #IVADO qui se tiendra à Montréal de janvier à mars 2026.
➡️ Inscriptions event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
➡️ Inscriptions event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
December 16, 2025 at 8:46 PM
🧠 Ingrédients computationnels du raisonnement : participez au prochain semestre thématique #IVADO qui se tiendra à Montréal de janvier à mars 2026.
➡️ Inscriptions event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
➡️ Inscriptions event.fourwaves.com/fr/thematics...
@glajoie.bsky.social @taylorwwebb.bsky.social @lampinen.bsky.social
For those attending the #CogInterp workshop at NeurIPS, please check out our work on visual symbolic mechanisms led by @rassouel.bsky.social and @thisisadax.bsky.social. We find that visual feature binding in VLMs is supported by emergent symbolic mechanisms.
December 7, 2025 at 6:45 PM
For those attending the #CogInterp workshop at NeurIPS, please check out our work on visual symbolic mechanisms led by @rassouel.bsky.social and @thisisadax.bsky.social. We find that visual feature binding in VLMs is supported by emergent symbolic mechanisms.
Reposted by Taylor Webb
1/ Why does RL struggle with social dilemmas? How can we ensure that AI learns to cooperate rather than compete?
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
December 3, 2025 at 7:19 PM
1/ Why does RL struggle with social dilemmas? How can we ensure that AI learns to cooperate rather than compete?
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
Introducing our new framework: MUPI (Embedded Universal Predictive Intelligence) which provides a theoretical basis for new cooperative solutions in RL.
Preprint🧵👇
(Paper link below.)
Reposted by Taylor Webb
1/9
🚨Thrilled to share "Caption This, Reason That", a #NeurIPS2025 Spotlight! 🔦
Meet us at #2112, 3 Dec 11 a.m.
We analyze VLM limitations through the lens of Cognitive Science (Perception, Attention, Memory) and propose a simple "Self-Captioning" method that boosts spatial reasoning by ~18%.
🧵👇
🚨Thrilled to share "Caption This, Reason That", a #NeurIPS2025 Spotlight! 🔦
Meet us at #2112, 3 Dec 11 a.m.
We analyze VLM limitations through the lens of Cognitive Science (Perception, Attention, Memory) and propose a simple "Self-Captioning" method that boosts spatial reasoning by ~18%.
🧵👇
December 1, 2025 at 4:43 PM
1/9
🚨Thrilled to share "Caption This, Reason That", a #NeurIPS2025 Spotlight! 🔦
Meet us at #2112, 3 Dec 11 a.m.
We analyze VLM limitations through the lens of Cognitive Science (Perception, Attention, Memory) and propose a simple "Self-Captioning" method that boosts spatial reasoning by ~18%.
🧵👇
🚨Thrilled to share "Caption This, Reason That", a #NeurIPS2025 Spotlight! 🔦
Meet us at #2112, 3 Dec 11 a.m.
We analyze VLM limitations through the lens of Cognitive Science (Perception, Attention, Memory) and propose a simple "Self-Captioning" method that boosts spatial reasoning by ~18%.
🧵👇
Reposted by Taylor Webb
Our paper “The cost of thinking is similar between large reasoning models and humans” is now out in PNAS! 🤖🧠
w/ @fepdelia.bsky.social, @hopekean.bsky.social, @lampinen.bsky.social, and @evfedorenko.bsky.social
Link: www.pnas.org/doi/10.1073/... (1/6)
w/ @fepdelia.bsky.social, @hopekean.bsky.social, @lampinen.bsky.social, and @evfedorenko.bsky.social
Link: www.pnas.org/doi/10.1073/... (1/6)
PNAS
Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...
www.pnas.org
November 19, 2025 at 8:14 PM
Our paper “The cost of thinking is similar between large reasoning models and humans” is now out in PNAS! 🤖🧠
w/ @fepdelia.bsky.social, @hopekean.bsky.social, @lampinen.bsky.social, and @evfedorenko.bsky.social
Link: www.pnas.org/doi/10.1073/... (1/6)
w/ @fepdelia.bsky.social, @hopekean.bsky.social, @lampinen.bsky.social, and @evfedorenko.bsky.social
Link: www.pnas.org/doi/10.1073/... (1/6)
Reposted by Taylor Webb
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
October 31, 2025 at 4:19 PM
LLMs are trained to compress data by mapping sequences to high-dim representations!
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
How does the complexity of this mapping change across LLM training? How does it relate to the model’s capabilities? 🤔
Announcing our #NeurIPS2025 📄 that dives into this.
🧵below
#AIResearch #MachineLearning #LLM
Reposted by Taylor Webb
this paper takes me by surprise a bit. of coz, we all know Ned's been thinking along these lines for decades: philpapers.org/rec/BLOBVC
but is he really gonna seriously publish a new paper on this now, given all the AI hype & debates re: how unscientific some popular views on C are these days?
1/
but is he really gonna seriously publish a new paper on this now, given all the AI hype & debates re: how unscientific some popular views on C are these days?
1/
October 9, 2025 at 2:40 AM
this paper takes me by surprise a bit. of coz, we all know Ned's been thinking along these lines for decades: philpapers.org/rec/BLOBVC
but is he really gonna seriously publish a new paper on this now, given all the AI hype & debates re: how unscientific some popular views on C are these days?
1/
but is he really gonna seriously publish a new paper on this now, given all the AI hype & debates re: how unscientific some popular views on C are these days?
1/
Very excited to share that our work (together with co-first author Shanka Subhra Mondal and @neuroai.bsky.social ) on a brain-inspired architecture for planning with LLMs is now out in Nature Communications! www.nature.com/articles/s41... (thread below)
A brain-inspired agentic architecture to improve planning with LLMs - Nature Communications
Multi-step planning is a challenge for LLMs. Here, the authors introduce a brain-inspired Modular Agentic Planner that decomposes planning into specialized LLM modules, improving performance across tasks and highlighting the value of cognitive neuroscience for LLM design.
www.nature.com
October 6, 2025 at 9:51 PM
Very excited to share that our work (together with co-first author Shanka Subhra Mondal and @neuroai.bsky.social ) on a brain-inspired architecture for planning with LLMs is now out in Nature Communications! www.nature.com/articles/s41... (thread below)
Very nice commentary arguing that binding is still a problem, for both biological and artificial neural networks www.sciencedirect.com/science/arti...
Feature binding in biological and artificial vision
www.sciencedirect.com
September 7, 2025 at 4:07 PM
Very nice commentary arguing that binding is still a problem, for both biological and artificial neural networks www.sciencedirect.com/science/arti...
Reposted by Taylor Webb
Very happy to announce that our paper “Sensory Horizons and the Functions of Conscious Vision” is now out as a target article in BBS!! @smfleming.bsky.social and I present a new theory of the evolution and functions of visual consciousness. Article here: doi.org/10.1017/S014.... A (long) thread 🧵
Sensory Horizons and the Functions of Conscious Vision | Behavioral and Brain Sciences | Cambridge Core
Sensory Horizons and the Functions of Conscious Vision
doi.org
April 21, 2025 at 3:27 PM
Very happy to announce that our paper “Sensory Horizons and the Functions of Conscious Vision” is now out as a target article in BBS!! @smfleming.bsky.social and I present a new theory of the evolution and functions of visual consciousness. Article here: doi.org/10.1017/S014.... A (long) thread 🧵
Reposted by Taylor Webb
🔍 Large language models, similar to those behind ChatGPT, can predict how the human brain responds to visual stimuli
New study by @adriendoerig.bsky.social @freieuniversitaet.bsky.social with colleagues from Osnabrück, Minnesota and @umontreal-en.bsky.social
Read the whole story 👉 bit.ly/3JXlYmO
New study by @adriendoerig.bsky.social @freieuniversitaet.bsky.social with colleagues from Osnabrück, Minnesota and @umontreal-en.bsky.social
Read the whole story 👉 bit.ly/3JXlYmO
September 2, 2025 at 7:01 AM
🔍 Large language models, similar to those behind ChatGPT, can predict how the human brain responds to visual stimuli
New study by @adriendoerig.bsky.social @freieuniversitaet.bsky.social with colleagues from Osnabrück, Minnesota and @umontreal-en.bsky.social
Read the whole story 👉 bit.ly/3JXlYmO
New study by @adriendoerig.bsky.social @freieuniversitaet.bsky.social with colleagues from Osnabrück, Minnesota and @umontreal-en.bsky.social
Read the whole story 👉 bit.ly/3JXlYmO