Taylor Webb

Whither symbols in the era of advanced neural networks? Some of the strongest evidence that human minds should be thought about in terms of symbolic systems has been the way they combine ideas, produce novelty, and learn quickly. We argue that modern neura...

I like this general point about levels of explanation (which I think is similar to the point we make here arxiv.org/abs/2508.05776) but how does it relate to the discussion about mistakes made by LLMs? (Possibly explained by the earlier context of the clip)

But this example again appears not to involve the reasoning mode. I agree that ‘thinking’ is confusing nomenclature but it’s notable that most (not all) of the stupidest mistakes come from the feedforward / parallel processing mode.

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models...

We also have a paper on this arxiv.org/abs/2411.00238 but it doesn’t seem to be an arbitrary failure. Instead they seem to fail in precisely the ways that human vision fails under time pressure (including with counting), and increasingly the models seem to resolve this via sequential processing.

Re: seeing vs. thinking, 'thinking' is arguably a bad term for this, in the vision setting the models depend on sequential processing to individuate objects but that wouldn't commonly be referred to as 'thinking' in the colloquial sense.

Huh, seems to be the result of different prompts, although it's arguably confusing to say that no liquid can be poured into it (at all or only in the current configuration?). In general most of the comically stupid mistakes (e.g. how many b's in blueberry) seem to be from the non-thinking models.

Funny, but these demos always seem to be the free / instant model. With thinking turned on it gets this correct.

very interesting! Consistent with this, we found that induction heads seem to be completely distinct from what we called 'symbolic induction heads' i.e. function vector heads arxiv.org/abs/2502.20332

How do you knock the induction heads out of an LM while preserving its ability to think? Is it even possible?

@keremsahin22.bsky.social's work is worth reading if you haven't seen it yet.

hapax.baulab.info

Memorization vs. generalization in deep learning: implicit biases, benign overfitting, and more Or: how I learned to stop worrying and love the memorization

What is the relationship between memorization and generalization in AI? Is there a fundamental tradeoff? In infinitefaculty.substack.com/p/memorizati... I’ve reviewed some of the evolving perspectives on memorization & generalization in machine learning, from classic perspectives through LLMs.

Unfortunately the event is in-person only.

Mechanistic Basis of Reasoning (in Brains and AI) | IVADO

Very excited for our second workshop on the computational ingredients of reasoning (Feb 24-27), this one focused on mechanisms of reasoning in both AI and the brain. Check out the program to see our amazing lineup of speakers, and please consider attending! ivado.ca/en/events/me...

Building compositional tasks with shared neural subspaces Nature - The brain can flexibly perform multiple tasks by compositionally combining task-relevant neural representations.

Thrilled that my paper is out in the @nature.com. We explored how the brain builds complex tasks by compositionally combining simpler sub-task representations. The brain flexibly performs multiple tasks by dynamically reusing neural subspaces for sensory inputs and motor actions

rdcu.be/eRVUk

Excited to announce a new book telling the story of mathematical approaches to studying the mind, from the origins of cognitive science to modern AI! The Laws of Thought will be published in February and is available for pre-order now.

That is, in order to do the kinds of things that are supposed to require algebraic / rule-based operations, these models actually do something that is algebraic, which both affirms the importance of algebraic operations for human-like reasoning and also shows it doesn't need to be innate.

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models Many recent studies have found evidence for emergent reasoning capabilities in large language models (LLMs), but debate persists concerning the robustness of these capabilities, and the extent to whic...

I generally agree, but the interesting thing is that the LLMs/VLMs sometimes do end up doing something very structured and algebraic, as we show e.g. here arxiv.org/abs/2502.20332 and here arxiv.org/abs/2506.15871 (the paper that @romanfeiman.bsky.social 's meme was commenting on).

Can you elaborate?

Very cool! Yeah would love to chat at some point.

Yes!

I'm curious, would you say that this sort of thing is consistent with the predictions of the LoT hypothesis, i.e. these models may emergently be implementing a LoT?

amazing summary of our work on visual symbolic mechanisms bsky.app/profile/this...

Thanks Shahab!

Excited to share that our work on Visual Symbolic Mechanisms has been accepted to ICLR! 🌴🇧🇷

Using Artificial Neural Networks to Relate External Sensory Features to Internal Decisional Evidence Abstract. All theories of perceptual decision-making postulate that external sensory information is transformed into the internal evidence that is used to judge the identity of the stimulus. However, ...

How do you know how visual stimuli are represented internally for decision making? This is perhaps the central question in perceptual decision making. In a new paper, we show that one can use artificial neural networks to crack this problem. #NeuroAi #VisionScience

direct.mit.edu/opmi/article...

YouTube video by Johns Hopkins University Apes Share Human Ability to Imagine

Imagination in bonobos!

I am thrilled to share a new paper w/ Amalia Bastos, out now in @science.org

We provide the first experimental evidence that a nonhuman animal can follow along a pretend scenario & track imaginary objects. Work w/ Kanzi, the bonobo, at Ape Initiative

youtu.be/NUSHcQQz2Ko

Very excited about this work looking at the emergent mechanisms that vision language models use to perform structured visual processing, mirroring a computational strategy (visual indexing) proposed in cognitive science, but here learned by VLMs. Check out the paper/thread for more details!

The visual world is composed of objects, and those objects are composed of features. But do VLMs exploit this compositional structure when processing multi-object scenes? In our 🆒🆕 #ICLR2026 paper, we find they do – via emergent symbolic mechanisms for visual binding. 🧵👇

This was a blast! Thanks for joining us!

Federal agents with weapons drawn, moments before murdering American citizens on the streets of Minneapolis at the dawn of 2026.

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...

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:🧵⬇️