Sign in

Max Kleiman-Weiner

@maxkw.bsky.social
4.4K followers 382 following 438 posts

professor at university of washington and scientist at Google DeepMind. computational cognitive scientist. working on social and artificial intelligence and alignment. faculty.washington.edu/maxkw

PostsRepliesMedia
Max Kleiman-Weiner @maxkw.bsky.social · 11/09/2026
Our newest work unifying game theoretic ideas about the evolution of cooperation with the emergence of computation itself. Self-replicating programs first emerge through random mutation and then spread by cooperating.
1205
Max Kleiman-Weiner @maxkw.bsky.social · 06/08/2026
New lab preprint! AI assistants are myopically helpful. Unlike caregivers that want to empower people and grow their long term autonomy, AI assistants interrupt independent thinking and jump right to the answer.
0173
Max Kleiman-Weiner @maxkw.bsky.social · 22/07/2026
Just arrived in Rio for #CogSci2026! I'll be at the Cognitive Science of AI Alignment workshop on Wednesay afternoon to talk about "Machines That Care Like Us"
0112
Max Kleiman-Weiner @maxkw.bsky.social · 05/06/2026
Excited about our new work measuring multi-turn persuasion in AI-human interactions and how to simulate human persuadability!
070
Reposted by Max Kleiman-Weiner
Jared Moore @jaredlcm.bsky.social · 05/06/2026
LLMs can shift people's beliefs. But most persuasion studies only check beliefs before and after a conversation. We built PersuasionTrace to measure beliefs turn by turn, so we can study how belief updates actually unfold.
An example human-target persuasion round with multi-turn persuasion tracing.
2125
Reposted by Max Kleiman-Weiner
cogscikid.bsky.social @cogscikid.bsky.social · 02/06/2026
Task diversity is supposedly key to generalization in RL. But what does it do to continual RL, where agents face one new task distribution after another? We find that past a point, more diversity actually inhibits continual reinforcement learning 🧵
45114
Reposted by Max Kleiman-Weiner
Kunal Jha @kjha02.bsky.social · 08/04/2026
Really excited to have the opportunity to give a talk on this work @cogscisociety.bsky.social !!! last year was a blast can’t wait to go back to Rio in July 🇧🇷 HUGE thanks to my collaborators for the support @aydanhuang265.bsky.social @EricYe29011995 @natashajaques.bsky.social @maxkw.bsky.social 🙏
092
Max Kleiman-Weiner @maxkw.bsky.social · 02/03/2026
Our new short piece in TiCS on intuitive theories of truth: how people judge whether statements could be true, whether statements are true, and whether to assert them as true. A great collab with @keremoktar.bsky.social @ihandleyminer.bsky.social @kevinzollman.com @lianeleeyoung.bsky.social
0277
Reposted by Max Kleiman-Weiner
Kunal Jha @kjha02.bsky.social · 10/02/2026
Can't wait to present this work @iclr-conf.bsky.social this year!!! Looking forward to hearing everyone's thoughts on the paper and learning more about peoples' research! Thanks again to my collaborators for all of their help on this project!
181
Reposted by Max Kleiman-Weiner
Stella Li @stellali.bsky.social · 25/11/2025
🤔💭What even is reasoning? It's time to answer the hard questions! We built the first unified taxonomy of 28 cognitive elements underlying reasoning Spoiler—LLMs commonly employ sequential reasoning, rarely self-awareness, and often fail to use correct reasoning structures🧠
2468
Reposted by Max Kleiman-Weiner
Kunal Jha @kjha02.bsky.social · 03/10/2025
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%...
33814
Max Kleiman-Weiner @maxkw.bsky.social · 03/10/2025
New paper challenges how we think about Theory of Mind. What if we model others as executing simple behavioral scripts rather than reasoning about complex mental states? Our algorithm, ROTE (Representing Others' Trajectories as Executables), treats behavior prediction as program synthesis.
2142
Max Kleiman-Weiner @maxkw.bsky.social · 02/10/2025
When values collide, what do LLMs choose? In our new paper, "Generative Value Conflicts Reveal LLM Priorities," we generate scenarios where values are traded off against each other. We find models prioritize "protective" values in multiple-choice, but shift toward "personal" values when interacting.
1100
Max Kleiman-Weiner @maxkw.bsky.social · 01/10/2025
Excited by our new work estimating the empowerment of LLM-based agents in text and code. Empowerment is the causal influence an agent has over its environment and measures an agent's capabilities without requiring knowledge of its goals or intentions.
3172
Max Kleiman-Weiner @maxkw.bsky.social · 06/08/2025
Claire's new work showing that when an assistant aims to optimize another's empowerment, it can lead to others being disempowered (both as a side effect and as an intentional outcome)!
070
Reposted by Max Kleiman-Weiner
Claire Yang @claireyang.bsky.social · 06/08/2025
Still catching up on my notes after my first #cogsci2025, but I'm so grateful for all the conversations and new friends and connections! I presented my poster "When Empowerment Disempowers" -- if we didn't get the chance to chat or you would like to chat more, please reach out!
Person standing next to poster titled "When Empowerment Disempowers"
0163
Reposted by Max Kleiman-Weiner
samuel mehr @mehr.nz · 31/07/2025
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
Max giving a talk w the slide in OP
2689
Max Kleiman-Weiner @maxkw.bsky.social · 22/07/2025
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/...
pnas.org
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...
29237
Reposted by Max Kleiman-Weiner
Kartik Chandra @kartikchandra.bsky.social · 18/07/2025
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!
1226
Max Kleiman-Weiner @maxkw.bsky.social · 17/07/2025
Very excited for this workshop!
0142
Reposted by Max Kleiman-Weiner
Cognitive Science Society @cogscisociety.bsky.social · 16/07/2025
#Workshop at #CogSci2025 Building computational models of social cognition in memo 🗓️ Wednesday, July 30 📍 Pacifica I - 8:30-10:00 🗣️ Kartik Chandra, Sean Dae Houlihan, and Max Kleiman-Weiner 🧑‍💻 underline.io/events/489/s...
Promotional image for a #CogSci2025 workshop titled “Building 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 “Theories of the Past / Theories of the Future,” and the dates: July 30–August 2 in San Francisco.
1122
Reposted by Max Kleiman-Weiner
Kempner Institute at Harvard University @kempnerinstitute.bsky.social · 15/07/2025
'Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination' @kjha02.bsky.social · Wilka Carvalho · Yancheng Liang · Simon Du · @maxkw.bsky.social · @natashajaques.bsky.social doi.org/10.48550/arX... (3/20)
162
Max Kleiman-Weiner @maxkw.bsky.social · 29/06/2025
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.
AI DOOM
060
Reposted by Max Kleiman-Weiner
Sofia Forss @sofiaforss.bsky.social · 28/06/2025
Thanks to the Diverse Intelligence Community for all these inspiring days & impressions in Sydney 🙏🏻 @chriskrupenye.bsky.social @katelaskowski.bsky.social @divintelligence.bsky.social @maxkw.bsky.social
0163
Max Kleiman-Weiner @maxkw.bsky.social · 09/06/2025
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!
1306
Max Kleiman-Weiner @maxkw.bsky.social · 28/04/2025
Excited to speak about some new work on Bayesian Cooperation at this workshop! Join us virtually
093
Reposted by Max Kleiman-Weiner
Tobias Gerstenberg @tobigerstenberg.bsky.social · 25/04/2025
Now out in JPSP ‼️ "Inference from social evaluation" with Zach Davis, Kelsey Allen, @maxkw.bsky.social, and @julianje.bsky.social 📃 (paper): psycnet.apa.org/record/2026-... 📜 (preprint): osf.io/preprints/ps...
25513
Reposted by Max Kleiman-Weiner
Kunal Jha @kjha02.bsky.social · 19/04/2025
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%...
1267
Max Kleiman-Weiner @maxkw.bsky.social · 19/04/2025
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.
030
Max Kleiman-Weiner @maxkw.bsky.social · 14/03/2025
How AlphaGo like architectures can explain human insight. Out now in Cognition!
0101
Reposted by Max Kleiman-Weiner
Alice Zhang @licezhang.bsky.social · 14/03/2025
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
sciencedirect.com
Similar failures of consideration arise in human and machine planning
Humans are remarkably efficient at decision making, even in “open-ended” problems where the set of possible actions is too large for exhaustive evalua…
1338
Max Kleiman-Weiner @maxkw.bsky.social · 13/02/2025
Accepted as a Spotlight in ICLR2025!
0100
Max Kleiman-Weiner @maxkw.bsky.social · 26/01/2025
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...
1201
Reposted by Max Kleiman-Weiner
Tobias Gerstenberg @tobigerstenberg.bsky.social · 23/01/2025
🔊 New paper just accepted in JPSP 🥳 In "Inference from social evaluation", we explore how people use social evaluations, such as judgments of blame or praise, to figure out what happened. 📜 osf.io/preprints/ps... 📎 github.com/cicl-stanfor... 1/6
26115
Max Kleiman-Weiner @maxkw.bsky.social · 09/01/2025
Very nice to see our work on LLM agent cooperation covered in Wired! www.wired.com/story/ai-soc...
wired.com
AI Social Media Users Are Not Always a Totally Dumb Idea
Meta’s AI characters users might seem useless, but fake social media users can sometimes offer valuable insights into real human behavior.
170
Max Kleiman-Weiner @maxkw.bsky.social · 15/12/2024
Josh Tenenbaum on scaling up vs growing up and the path to human-like reasoning #NeurIPS2024
1826
Max Kleiman-Weiner @maxkw.bsky.social · 14/12/2024
Honored to receive the Best Paper Award at the #NeurIPS2024 Pluralistic Alignment Workshop Check out our preprint "Language Model Alignment in Multilingual Trolley Problems" at arxiv.org/pdf/2407.02273!
arxiv.org
1252
Reposted by Max Kleiman-Weiner
Kunal Jha @kjha02.bsky.social · 12/12/2024
Really excited to present my work this Sunday @NeurIPS on how we might approach training a generalist agent capable of cooperation at scale: coordinating with many novel partners on many novel tasks has never been easier! Come by the IMOL workshop to check it out and chat more!
0113
Max Kleiman-Weiner @maxkw.bsky.social · 11/12/2024
Come hang!
040
Reposted by Max Kleiman-Weiner
Reinforcement Learning Conference @rl-conference.bsky.social · 11/12/2024
Now with a luma link: lu.ma/1bxqun5l
lu.ma
RL Social (Sponsored by RLC) · Luma
RL social sponsored by RLC! Come meet all the RL researchers at NeurIPS. Note: requires NeurIPS badge or prior knowledge of who you are.
071
Max Kleiman-Weiner @maxkw.bsky.social · 10/12/2024
Only at NeurIPS
2431
Max Kleiman-Weiner @maxkw.bsky.social · 05/12/2024
Excited that our multi-agent LLM agent work, “Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents,” will be presented at #NeurIPS24 -- reach out if you want to meet up in Vancouver!
1287
Max Kleiman-Weiner @maxkw.bsky.social · 26/11/2024
Github Copilot output. A sad but fascinating alignment failure. Reveals hidden LLM biases by going out of their RLHF distribution
3152
Reposted by Max Kleiman-Weiner
Julia Leonard @julia-a-leonard.bsky.social · 22/11/2024
Overparenting is on the rise and hurts children’s motivation starting in early childhood. How can we help parents step back? Our new paper in Child Dev shows that pointing out learning opportunities reduces overparenting. srcd.onlinelibrary.wiley.com/doi/10.1111/...
srcd.onlinelibrary.wiley.com
<em>Child Development</em> | SRCD Journal | Wiley Online Library
Overparenting—taking over and completing developmentally appropriate tasks for children—is pervasive and hurts children's motivation. Can overparenting in early childhood be reduced by simply framing...
29531
Max Kleiman-Weiner @maxkw.bsky.social · 19/11/2024
The computational cognitive science starter kit
1235
Max Kleiman-Weiner @maxkw.bsky.social · 15/11/2024
I’m recruiting PhD students to join the Computational Minds and Machines Lab at the University of Washington in Seattle! Join us to work at the intersection of computational cognitive science and AI with a broad focus on social intelligence. (Please reshare!)
13313
Reposted by Max Kleiman-Weiner
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 13/11/2024
Got it started go.bsky.app/9gsefkW
4196
Reposted by Max Kleiman-Weiner
xuan (ɕɥɛn / sh-yen) @xuanalogue.bsky.social · 11/11/2024
Okay the people requested one so here is an attempt at a Computational Cognitive Science starter pack -- with apologies to everyone I've missed! LMK if there's anyone I should add! go.bsky.app/KDTg6pv
7021991
Max Kleiman-Weiner @maxkw.bsky.social · 11/11/2024
These videos of a humanoid watching itself in a mirror are a cool test of a “self” model. The robot’s world model tries to predict the next visual inputs. It can predict its own movements from a first-person view but doesn’t map the mirrored body to its own, and thus, the
100
Max Kleiman-Weiner @maxkw.bsky.social · 11/11/2024
These videos of a humanoid watching itself in a mirror are a cool test of a “self” model. The robot’s world model tries to predict the next visual inputs. It can predict its movements from a first-person view but doesn’t map the mirrored body to its own, and thus, the mirrored view doesn't match.
150