Lightnews — Scholar-powered news

Reposted by Fred Callaway

Kunal Jha @kjha02.bsky.social · 6d

Forget modeling every belief and goal! What if we represented people as following simple scripts instead (i.e "cross the crosswalk")?

Our new paper shows AI which models others’ minds as Python code 💻 can quickly and accurately predict human behavior!

shorturl.at/siUYI%F0%9F%...

3 14 36

Reposted by Fred Callaway

Alireza Modirshanechi @modirshanechi.bsky.social · 10d

New in @pnas.org: doi.org/10.1073/pnas...

We study how humans explore a 61-state environment with a stochastic region that mimics a “noisy-TV.”

Results: Participants keep exploring the stochastic part even when it’s unhelpful, and novelty-seeking best explains this behavior.

#cogsci #neuroskyence

35 92

Reposted by Fred Callaway

xavier roberts-gaal @xrg.bsky.social · 23d

We often hear from reviewers: "what about demand effects?" So we developed a method to eliminate them. Something weird happened during testing: We couldn’t detect demand effects in the first place! (1/8)

Summary of design and results from our three studies. (A: Design) Each study used a similar experimental design, measuring both positive and negative demand in an online experiment, with three commonly-used task types (dictator game, vignette, intervention). Our experiments had ns ≈ 250 per cell. (B: Results) Observed demand effects were statistically indistinguishable from zero. The plot shows means and 95% confidence intervals for standardized mean differences derived from frequentist analyses of each experiment and an inverse variance-weighted fixed-effect estimator pooling all experiments (solid bars). Prior measurements of experimenter demand from a previous dictator game experiment (de Quidt et al., 2018; standardized mean difference from regression coefficient) and a meta-analysis primarily including small-sample, in-person studies (Coles et al., 2025; Hedge’s g statistic) are also shown for comparison (striped bars). The main text includes Bayesian analyses that quantify our uncertainty.

3 39 82

Reposted by Fred Callaway

Tess Forest @tessforest.bsky.social · Aug 6

Happy to share "The Dynamics of Caregiver Unpredictability Shape Moment-to-Moment Infant Looking During Dyadic Interaction," out now in Child Development thanks to a large team of people I worked on this with! srcd.onlinelibrary.wiley.com/doi/pdfdirec...

<em>Child Development</em> | SRCD Journal | Wiley Online Library

Cognitive development is associated with how predictable caregivers are, but the mechanisms driving this are unclear. One possibility is caregiver predictability initially shapes how infants gather i...

srcd.onlinelibrary.wiley.com

1 10 27

Reposted by Fred Callaway

Max Kleiman-Weiner @maxkw.bsky.social · Jul 22

Our new paper is out in PNAS: "Evolving general cooperation with a Bayesian theory of mind"!

Humans are the ultimate cooperators. We coordinate on a scale and scope no other species (nor AI) can match. What makes this possible? 🧵

www.pnas.org/doi/10.1073/...

Evolving general cooperation with a Bayesian theory of mind | PNAS

Theories of the evolution of cooperation through reciprocity explain how unrelated self-interested individuals can accomplish more together than th...

www.pnas.org

2 36 92

Fred Callaway @fredcallaway.bsky.social · Jul 14

@stepalminteri.bsky.social et al. made this point 8 years ago

www.cell.com/trends/cogni...

The Importance of Falsification in Computational Cognitive Modeling

In the past decade the field of cognitive sciences has seen an exponential growth in the number of computational modeling studies. Previous work has indicated why and how candidate models of cognition...

www.cell.com

9

Fred Callaway @fredcallaway.bsky.social · Jul 14

Centaur's performance may be largely driven by learning a good model of behavioral auto-regression—independent of the task. An important lesson for cognitive modelers: higher likelihood ≠ better account of behavior.

osf.io/preprints/ps...

OSF

osf.io

1 4 21

Fred Callaway @fredcallaway.bsky.social · Jul 14

If you include emotion recognition in "physiognomy", sure—but that's an unusual use of the term. If (1) people with PTSD have a different distribution of emotional responses and (2) emotional state can be inferred from facial expression, then it follows that one can infer PTSD from images.

1 1

Fred Callaway @fredcallaway.bsky.social · Jul 13

Completely agree. I just think it’s in all of our interests if we are as precise as possible when criticizing irresponsible use of AI. The cultural bias point is a strong one. I’m less sure about the blanket statement that a statistical model can’t do what’s claimed here *in principle*.

1

Fred Callaway @fredcallaway.bsky.social · Jul 13

I must be misunderstanding you, but don’t people detect emotion (internal mental state) from facial expression all the time?

2

Reposted by Fred Callaway

Simon Kern @skjerns.de · Jun 16

preprint alert 🚨
1/ Can we accurately detect sequential replay in humans using Temporally Delayed Linear Modelling (#TDLM)? In our recent study, we could not find any replay and decided to dig deeper by running a hybrid simulation with surprising results. Link to preprint & details below 👇

2 27 55

Reposted by Fred Callaway

Angelo Forli @aforli89.bsky.social · Jul 9

Our study is out in Nature!
Using wireless Neuropixels we recorded hippocampal activity in freely flying bats and uncovered replay and theta(less) sweeps, revealing striking differences from classic rodent models.

👉 www.nature.com/articles/s41...

Replay and representation dynamics in the hippocampus of freely flying bats - Nature

Nature - Replay and representation dynamics in the hippocampus of freely flying bats

www.nature.com

7 32 120

Fred Callaway @fredcallaway.bsky.social · Jul 9

I asked ChatGPT to respond to this critique. It replies:

"That’s a sharp observation—and honestly, a fair one. ChatGPT can sound overly agreeable or eager to please, much like..."

Image of ChatGPT output, which reads:

That’s a sharp observation—and honestly, a fair one. ChatGPT can sound overly agreeable or eager to please, much like the tone often found in author rebuttals to peer review. That tone is partly intentional: it’s designed to be polite, constructive, and deferential to the user. But you’re right—it can veer into sycophancy, especially when clarity or critical thinking should take precedence over friendliness.

As for contradicting itself while continuing to “agree”: that’s a deeper issue. It can happen when the model tries to accommodate multiple inputs without weighing them critically or fails to maintain internal consistency across a longer exchange. The root problem isn’t just tone—it’s a mix of conversational bias, lack of persistent memory, and insufficient pushback against flawed logic.

So yes, the comparison to author response letters is apt. And unlike those letters, ChatGPT doesn’t have professional incentives to fake deference—but the algorithmic incentives can still push it in that direction. Would you prefer a more candid, opinionated tone from me in general?

3

Reposted by Fred Callaway

Robin Mar-Witch 🧙🏻‍♀️ @electricland.bsky.social · Jul 6

Stop spreading this garbage about em dashes in ACTUAL EDITED PROSE OH MY GOD.

Plenty of actual human beings know how to type em dashes! We’re called “writers” and “editors” — maybe you’ve heard of us?

340 1K 5K

Reposted by Fred Callaway

Christian Wolf @chriswolfvision.bsky.social · Jul 5

After all these reports of authors adding language instructions for LLM reviews in their papers I wanted to check this myself and I downloaded the .tex source from one of these papers.

Here is an example.
(I will not share the identity of the paper)

16 130 390

Fred Callaway @fredcallaway.bsky.social · Jul 5

Evidence for model-based meta-control? I look forward to reading!

Paul Sharp @paulbsharp.bsky.social · Jul 5

🚨New preprint! WHEN should we plan toward a goal? Most research focuses on how and where to plan, but the timing of planning initiation has been overlooked. We show humans leverage a cognitive map - called model-based meta-control - to learn when to deploy a plan.
🧵(1/15)
osf.io/preprints/ps...

1 7

Fred Callaway @fredcallaway.bsky.social · Jun 25

🔥Hot Take: When you quote the middle of a sentence at the end of your sentence, the period should be *after* the quote, as in "the middle of a sentence". Don't put your punctuation in my mouth.

1

Fred Callaway @fredcallaway.bsky.social · Jun 24

Super excited for this conference on mental health and adaptation to uncertainty. Remarkable how the organizers built a speaker lineup that is so interdisciplinary and yet so thematically focused. And the location certainly doesn't hurt...

www.fens.org/news-activit...

2

Reposted by Fred Callaway

Randall Munroe @xkcd.com · Jun 23

Tukey

xkcd.com/3104/

Comic. [block quote] “Far better an approximate answer to the *right* question, which is often vague, than an *exact* answer to the wrong question, which can always be made precise.” -John W. Tukey, The Future of Data Analysis (1962) [caption] Happy Approximate Birthday to John Tukey, author of my favorite statistics quote, who was born 110.000 years ago sometime this week.

19 430 2.9K

Reposted by Fred Callaway

Mike Wagner @prowag.bsky.social · Jun 19

Our latest @cccr.bsky.social survey reveals how unpopular the president’s most notable policy changes are with the American public. The survey also highlights the diversity of views within the GOP, related to their information diets, as well as US economic attitudes. cccr.wisc.edu/wp-content/u...

cccr.wisc.edu

12 24

Fred Callaway @fredcallaway.bsky.social · Jun 10

Compelling and thorough evidence for a very cool idea. Awesome paper.

Sam McDougle @actlab.bsky.social · Jun 2

Thrilled to share the new paper from the lab out today in
@nathumbehav.nature.com, led by the great @jetrach.bsky.social!

"Mental graphs structure the storage and retrieval of visuomotor associations"

www.nature.com/articles/s41...

Mental graphs structure the storage and retrieval of visuomotor associations - Nature Human Behaviour

Trach and McDougle show that motor responses can form part of structured, graph-like memory representations.

www.nature.com

2 5

Reposted by Fred Callaway

Ari Kahn @arikahn.bsky.social · Jun 5

I'm thrilled to announce that I will start as an Assistant Professor in Psychology & Cognitive Science at the University of Arizona in Jan 2026! My lab will investigate human planning and decision making through a combination of computational models, behavior, and fMRI (1/2)

4 5 58

Fred Callaway @fredcallaway.bsky.social · Jun 10

Congrats Ari!

1

Reposted by Fred Callaway

Marlos C. Machado @marloscmachado.bsky.social · May 24

📢 I'm happy to share the preprint: _Reward-Aware Proto-Representations in Reinforcement Learning_ ‼️

My PhD student, Hon Tik Tse, led this work, and my MSc student, Siddarth Chandrasekar, assisted us.

arxiv.org/abs/2505.16217

Basically, it's the SR with rewards. See below 👇

2 10 41