Max Kleiman-Weiner's Avatar

Max Kleiman-Weiner

@maxkw.bsky.social

professor at university of washington and founder at csm.ai. computational cognitive scientist. working on social and artificial intelligence and alignment. http://faculty.washington.edu/maxkw/

4,112 Followers  |  366 Following  |  422 Posts  |  Joined: 13.09.2023  |  2.3455

Latest posts by maxkw.bsky.social on Bluesky

It’s forgivable =) We just do the best we can with what we have (i.e., resource rational) 🀣

31.07.2025 23:56 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Max giving a talk w the slide in OP

Max giving a talk w the slide in OP

lol this may be the most cogsci cogsci slide I've ever seen, from @maxkw.bsky.social

"before I got married I had six theories about raising children, now I have six kids and no theories"......but here's another theory #cogsci2025

31.07.2025 18:18 β€” πŸ‘ 66    πŸ” 10    πŸ’¬ 2    πŸ“Œ 1
Preview
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...

Quantifying the cooperative advantage shows why humans, the most sophisticated cooperators, also have the most sophisticated machinery for understanding the minds of others. It also offers principles for building more cooperative AI systems. Check out the full paper!

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

22.07.2025 06:03 β€” πŸ‘ 7    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0
Post image

Finally, when we tested it against memory-1 strategies (such as TFT and WSLS) in the iterated prisoner's dilemma, the Bayesian Reciprocator: expanded the range where cooperation is possible and dominated prior algorithms using the *same* model across simultaneous & sequential games.

22.07.2025 06:03 β€” πŸ‘ 5    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

Even in one-shot games with observability, the Bayesian Reciprocator learns from observing others' interactions and enables cooperation through indirect reciprocity

22.07.2025 06:03 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

In dyadic repeated interactions in the Game Generator, the Bayesian Reciprocator quickly learns to distinguish cooperators from cheaters, remains robust to errors, and achieves high population payoffs through sustained cooperation.

22.07.2025 06:03 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0
Post image

Instead of just testing on repeated prisoners' dilemma, we created a "Game Generator" which creates infinite cooperation challenges where no two interactions are alike. Many classic games, like the prisoner’s dilemma or resource allocation games, are just special cases.

22.07.2025 06:03 β€” πŸ‘ 8    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

It uses theory of mind to infer the latent utility functions of others through Bayesian inference and an abstract utility calculus to work across ANY game.

22.07.2025 06:03 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

We introduce the "Bayesian Reciprocator," an agent that cooperates with others proportional to its belief that others share its utility function.

22.07.2025 06:03 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Classic models of cooperation like tit-for-tat are simple but brittle. They only work in specific games, can't handle noise and stochasticity and don't understand others' intentions. But human cooperation is remarkably flexible and robust. How and why?

22.07.2025 06:03 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

This project was first presented back in 2018 (!) and was born from a collaboration between Alejandro Vientos, Dave Rand @dgrand.bsky.social & Josh Tenenbaum @joshtenenbaum.bsky.social

22.07.2025 06:03 β€” πŸ‘ 7    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
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...

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/...

22.07.2025 06:03 β€” πŸ‘ 91    πŸ” 36    πŸ’¬ 2    πŸ“Œ 2

As always, CogSci has a fantastic lineup of workshops this year. An embarrassment of riches!

Still deciding which to pick? If you are interested in building computational models of social cognition, I hope you consider joining @maxkw.bsky.social, @dae.bsky.social, and me for a crash course on memo!

18.07.2025 13:56 β€” πŸ‘ 21    πŸ” 6    πŸ’¬ 1    πŸ“Œ 0

Very excited for this workshop!

17.07.2025 04:42 β€” πŸ‘ 14    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0
Promotional image for a #CogSci2025 workshop titled β€œBuilding computational models of social cognition in memo.” Organized and presented by Kartik Chandra, Sean Dae Houlihan, and Max Kleiman-Weiner. Scheduled for July 30 at 8:30 AM in room Pacifica I. The banner features the conference theme β€œTheories of the Past / Theories of the Future,” and the dates: July 30–August 2 in San Francisco.

Promotional image for a #CogSci2025 workshop titled β€œBuilding computational models of social cognition in memo.” Organized and presented by Kartik Chandra, Sean Dae Houlihan, and Max Kleiman-Weiner. Scheduled for July 30 at 8:30 AM in room Pacifica I. The banner features the conference theme β€œTheories of the Past / Theories of the Future,” and the dates: July 30–August 2 in San Francisco.

#Workshop at #CogSci2025
Building computational models of social cognition in memo

πŸ—“οΈ Wednesday, July 30
πŸ“ Pacifica I - 8:30-10:00
πŸ—£οΈ Kartik Chandra, Sean Dae Houlihan, and Max Kleiman-Weiner
πŸ§‘β€πŸ’» underline.io/events/489/s...

16.07.2025 20:32 β€” πŸ‘ 11    πŸ” 2    πŸ’¬ 1    πŸ“Œ 2
Post image

'Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination'

@kjha02.bsky.social Β· Wilka Carvalho Β· Yancheng Liang Β· Simon Du Β·
@maxkw.bsky.social Β· @natashajaques.bsky.social

doi.org/10.48550/arX...

(3/20)

15.07.2025 13:44 β€” πŸ‘ 6    πŸ” 2    πŸ’¬ 1    πŸ“Œ 0
AI DOOM

AI DOOM

Settling in for my flight and apparently A.I. DOOM is now a movie genre between Harry Potter and Classics. Nothing better than an existential crisis with pretzels and a ginger ale.

29.06.2025 22:52 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image Post image

Thanks to the Diverse Intelligence Community for all these inspiring days & impressions in Sydney πŸ™πŸ» @chriskrupenye.bsky.social @katelaskowski.bsky.social @divintelligence.bsky.social @maxkw.bsky.social

28.06.2025 03:46 β€” πŸ‘ 16    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0

And a more detailed thread from the lead authors
Tianyi (Alex) Qiu and Zhonghao He, who both did an incredible job with this work: x.com/Tianyi_Alex_...

09.06.2025 20:23 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
The Lock-in Hypothesis: Stagnation by Algorithm The training and deployment of large language models (LLMs) create a feedback loop with human users: models learn human beliefs from data, reinforce these beliefs with generated content, reabsorb the ...

Check out the paper here:
arxiv.org/abs/2506.06166

09.06.2025 20:23 β€” πŸ‘ 5    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

LLMs learn beliefs and values from human data, influence our opinions, and then reabsorb those influenced beliefs, feeding them back to users again and again. We call this the "Lock-In Hypothesis" and develop theory, simulations, and empirics to test it in our latest ICML paper!

09.06.2025 20:23 β€” πŸ‘ 30    πŸ” 6    πŸ’¬ 1    πŸ“Œ 0

Congrats Fred! Awesome news!

08.05.2025 07:27 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Excited to speak about some new work on Bayesian Cooperation at this workshop! Join us virtually

28.04.2025 21:14 β€” πŸ‘ 10    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0
Post image

Now out in JPSP ‼️

"Inference from social evaluation" with Zach Davis, Kelsey Allen, @maxkw.bsky.social, and @julianje.bsky.social

πŸ“ƒ (paper): psycnet.apa.org/record/2026-...
πŸ“œ (preprint): osf.io/preprints/ps...

25.04.2025 15:55 β€” πŸ‘ 56    πŸ” 13    πŸ’¬ 2    πŸ“Œ 0
Post image

Our new paper (first one of my PhD!) on cooperative AI reveals a surprising insight: Environment Diversity > Partner Diversity.

Agents trained in self-play across many environments learn cooperative norms that transfer to humans on novel tasks.

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

19.04.2025 00:06 β€” πŸ‘ 25    πŸ” 7    πŸ’¬ 1    πŸ“Œ 5

Awesome new work from my lab led by @kjha02.bsky.social scaling cooperative AI! True cooperation requires adapting to both unfamiliar partners and novel environments. Agents trained with CEC get us closer to agents that can act with general cooperative principles rather than memorized strategies.

19.04.2025 06:24 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

How AlphaGo like architectures can explain human insight. Out now in Cognition!

14.03.2025 15:26 β€” πŸ‘ 10    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0
Preview
Similar failures of consideration arise in human and machine planning Humans are remarkably efficient at decision making, even in β€œopen-ended” problems where the set of possible actions is too large for exhaustive evalua…

my paper with max, @maxkw.bsky.social, tuomas, and @fierycushman.bsky.social out in cognition at long last www.sciencedirect.com/science/arti...

We explain why humans and successful AI planners both fail on a certain kind of problem that we might describe as requiring insight or creativity

14.03.2025 15:21 β€” πŸ‘ 32    πŸ” 8    πŸ’¬ 1    πŸ“Œ 1

Accepted as a Spotlight in ICLR2025!

13.02.2025 23:43 β€” πŸ‘ 10    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Emergent transition from code to natural language for reasoning tasks when RL tuning a language model for math. Interesting to consider implications for "Language of Thought" style theories in cognition.

hkust-nlp.notion.site/simplerl-rea...

26.01.2025 06:32 β€” πŸ‘ 20    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0

@maxkw is following 20 prominent accounts