Incredibly excited about this direction: automating scientific discovery in cognitive science, with agents designing targeted experiments, collecting human data, and using the results to refine their theories. We show that this loop can lead to models that better predict human behavior!

Fun story about this paper, which I'm really excited about! This came out of a classic nerdswipe by @noahdgoodman.bsky.social - we were teaching together this winter and he said "is it time for robots to do psychology?"

Really proud to be part of this dream team! We make a strong case for end-to-end systems that can not only propose new cognitive theories but *validate* them by collecting human data! ✨ Check out project lead Ben’s thread for the highlights and a link to our preprint!

New preprint! AI agents have shown impressive scientific automation capabilities. Can we apply them to psychology research, *including* human data collection? We introduce auto-psych, a framework that proposes cognitive models and uses them to design and run human experiments. 1/

1st published paper alert ⚠️ in which @mcxfrank.bsky.social and I ask: How robust is the “shape bias”? a phenomenon that has been central to theories of early word learning: If a child hears a new word for an object, they often extend it to other objects with the same shape. tinyurl.com/JCL-shapebias

1/ 🚨 New opinion piece: "Can we automatize scientific discovery in the cognitive sciences?" We lay out a vision for a fully automated, in-silico science of the mind, where modern AI systems run every stage of the scientific discovery cycle in cognitive science 🧵 #AutomatedDiscovery #AI4Science

Join us at both conferences this summer! Our #CogSci2026 workshop features a series of invited talks on problem representations and abstractions. Our #CCN2026 community event opens a broader discussion on naturalistic problem solving: frameworks, tasks, methods, and where the field should go next.

🚨New preprint!🚨 We know that LM representations can be used to predict brain responses to language. But what *features* of these representations underlie this alignment? We use SAEs to find out!

1/ New preprint! Reasoning models often require hundreds of task examples and thousands of rollouts to improve on a task. How can they learn more from much less? Introducing CORE: contrastive self-reflection for rapid, sample-efficient, and interpretable self-improvement 🧵

We've updated the preprint of our Naturalistic Computational Cognitive Science paper (arxiv.org/abs/2502.20349) — we've tried to clarify and streamline the arguments, and added some new examples: 1/5

🤖🧠NEW PAPER🧠🤖 Children & neural networks can learn syntax from linear strings of words. How do they do it? Our hypothesis: Word co-occurrence statistics provide cues to syntax! (I.e., a new type of bootstrapping to consider!) Paper: arxiv.org/abs/2605.20529 1/n

1/ New preprint with @dyamins.bsky.social + team! Ventral visual representations within areas evolve over the course of the response along the same hierarchical complexity axis that distinguishes the visual areas, potentially driven by local recurrence.

1\ Can you make this Roman-numeral equation true by moving exactly one matchstick?

What is a psychological theory? Here's our take on this tricky and controversial question in this week's Experimentology chapter summary. Many things called "theories" in psychology aren't actually theories — they're frameworks. 🧵 experimentology.io

Thrilled to be sharing my latest work at #CogSci2026! Many of the spaces we move through, from kitchens to airports, were designed with specific uses in mind. How do people create such environments, and how do users figure out what they were designed for? 📃 osf.io/preprints/ps...

Many of us were taught experiments are for testing hypotheses. In Ch 1 of Experimentology, our free, open methods textbook, my coauthors and I argue differently: experiments are for estimating the magnitude of causal effects. This reframing has important consequences. 🧵 experimentology.io

New opinion piece on the interface between research on concepts and categories in minds vs. in neural network LMs! I take the position that there is much to be learned from this interface (e.g., learning about concepts from language alone) and outline some directions for future.

Goodfire released a megapost of all the random feature geometry stuff they're finding, and it's worth a read

🚨 New preprint w/ Valerio Rubino and Peter Dayan: how do people discover and use compositional structure under constraints? osf.io/preprints/ps... A key factor is a simple heuristic that favors reuse of repeated and symmetric fragments across scales, is robust to time pressure, and sped up RTs 🧵👇

We're happy to release NeuralSet: a simple, fast, scalable package for Neuro-AI Supports: 🧠 fMRI, EEG, MEG, iEEG, spikes… preprocessing 💬 text 🔊 audio ▶️ video 🏞️ image… embeddings 📦 pip install neuralset 🔍 facebookresearch.github.io/neuroai/neur... 📄 kingjr.github.io/files/neural... 🧵 Details👇

Announcing a new version of our 2024 paper on linguistic hypothesis generation from LMs! @najoung.bsky.social and I have systematized our hypothesis generation framework, added stringent criteria for model selection, 10x-ed our learning trials, and included an epigraph from Jeff Elman 🙏!

Children exhibit visual understanding from limited experience, orders of magnitude less than our best models. We introduce the Zero-shot World Model (ZWM). Trained on a single child's visual experience, BabyZWM rapidly generates competence across diverse benchmarks with no task-specific training. 🧵

Come join us! We have two research coordinator positions open with the Stanford IRISS predoctoral program, a program designed to mentor students for graduate study: LEVANTE: careersearch.stanford.edu/jobs/iriss-p... BabyView: careersearch.stanford.edu/jobs/iriss-p... (deadline 5/1)

The Cognitive Tools Lab at Stanford (cogtoolslab.github.io) is recruiting two new research staff members to join in AY 26-27. Full-Time Lab Manager: forms.gle/UVwfx5wbY9Km.... IRiSS Predoc Researcher: iriss.stanford.edu/predoc/2026-.... Please share widely in your networks, thank you!!

The Causality in Cognition Lab -- a supportive, bluesky-colored team -- is looking for a predoc to join us! Here are infos about the lab (cicl.stanford.edu) and the position (careersearch.stanford.edu/jobs/iriss-p...). The application deadline is May 1st. Please share, thank you 🙏

Excited to share our new publication, “Measuring Naturalistic Speech Comprehension in Real Time”! ➡️ rdcu.be/fa3hk #psynomBRM w/ @kriesjill.bsky.social, Shiven Gupta, Maria Papworth Burrel, & @lauragwilliams.bsky.social 🧵1/11

Disturbing anecdotal reports of "AI psychosis" and negative psychological effects have been emerging in the news. But what actually happens during these lengthy delusional "spirals"? In our preprint, we analyze chat logs from 19 users who experienced severe psychological harm🧵👇

Pleased to share that our paper "Representation Biases: Variance is Not Always a Good Proxy for Importance" is now out as Theory/New Concepts paper in eNeuro! www.eneuro.org/content/13/3... 1/

Can LLMs use ToM to genuinely persuade you, or do they just use good rhetoric? In our new preprint, we use the MINDGAMES framework to test this. Surprisingly, LLMs like o3 can be incredibly effective persuaders *without* actually understanding your mental states. 🧵👇

🚨New preprint! In-context learning underlies LLMs’ real-world utility, but what are its limits? Can LLMs learn completely novel representations in-context and flexibly deploy them to solve tasks? In other words, can LLMs construct an in-context world model? Let’s see! 👀

How do diverse context structures reshape representations in LLMs? In our new work, we explore this via representational straightening. We found LLMs are like a Swiss Army knife: they select different computational mechanisms reflected in different representational structures. 1/

Why don’t neural networks learn all at once, but instead progress from simple to complex solutions? And what does “simple” even mean across different neural network architectures? Sharing our new paper @iclr_conf led by Yedi Zhang with Peter Latham arxiv.org/abs/2512.20607

New paper! In arxiv.org/abs/2601.20834 we study how language models representations of things like factuality evolve over a conversation. We find that in edge case conversations, e.g. about model consciousness or delusional content, model representations can change dramatically! 1/

@summerfieldlab.bsky.social and I are very happy to share this paper! Building on work by @scychan.bsky.social, we show that how people learn depends on the distribution of examples they see, and changes in a way that’s very similar to transformer models.

I think that if you hypothesize that learning may dominate (aspects of) what the system acquires, then they can be useful as models of that portion of the process — bearing in mind that like any model (organism), they are wrong. They offer a way of testing hypotheses about 1/3

new: Eric Bigelow @ericbigelow.bsky.social suggests the 2 main ways of controlling LLMs (prompting & steering) can be understood as changing model beliefs (as in Bayesian belief updating) "Belief Dynamics Reveal the Dual Nature of In-Context Learning & Activation Steering" arxiv.org/pdf/2511.00617

The Harvard Gazette has a nice story on my student @yangxiang.bsky.social and her work with @tobigerstenberg.bsky.social news.harvard.edu/gazette/stor...

What aspects of human knowledge do vision models like CLIP fail to capture, and how can we improve them? We suggest models miss key global organization; aligning them makes them more robust. Check out LukasMuttenthaler's work, finally out (in Nature!?) www.nature.com/articles/s41... + our blog! 1/3

In LLMs, concepts aren’t static: they evolve through time and have rich temporal dependencies. We introduce Temporal Feature Analysis (TFA) to separate what's inferred from context vs. novel information. A big effort led by @ekdeepl.bsky.social, @sumedh-hindupur.bsky.social, @canrager.bsky.social!

Humans and LLMs think fast and slow. Do SAEs recover slow concepts in LLMs? Not really. Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.

Excited to have this out! This was a fun project that started with YingQiao and I discussing whether VLMs can do mental simulation of physics like people do, and it culminated in a new method where we prompted image generation models to simulate a series of images frame-by-frame.

🚨 NEW PREPRINT: Multimodal inference through mental simulation. We examine how people figure out what happened by combining visual and auditory evidence through mental simulation. Paper: osf.io/preprints/ps... Code: github.com/cicl-stanfor...

🚨New paper out w/ @gershbrain.bsky.social & @fierycushman.bsky.social from my time @Harvard! Humans are capable of sophisticated theory of mind, but when do we use it? We formalize & document a new cognitive shortcut: belief neglect — inferring others' preferences, as if their beliefs are correct🧵

*Sharing for our department’s trainees* 🧠 Looking for insight on applying to PhD programs in psychology? ✨ Apply by Sep 25th to Stanford Psychology's 9th annual Paths to a Psychology PhD info-session/workshop to have all of your questions answered! 📝 Application: tinyurl.com/pathstophd2025

In neuroscience, we often try to understand systems by analyzing their representations — using tools like regression or RSA. But are these analyses biased towards discovering a subset of what a system represents? If you're interested in this question, check out our new commentary! Thread:

Super excited to have the #InfoCog workshop this year at #CogSci2025! Join us in SF for an exciting lineup of speakers and panelists, and check out the workshop's website for more info and detailed scheduled sites.google.com/view/infocog...

Submit your latest and greatest papers to the hottest workshop on the block---on cognitive interpretability! 🔥

Excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣 How can we interpret the algorithms and representations underlying complex behavior in deep learning models? 🌐 coginterp.github.io/neurips2025/ 1/4

A bias for simplicity by itself does not guarantee good generalization (see the No Free Lunch Theorems). So an inductive bias is only good to the extent that it reflects structure in the data. Is the world simple? The success of deep nets (with their intrinsic Occam's razor) would suggest yes(?)

Really nice analysis!