Profile avatar
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/
402 posts 3,859 followers 362 following
Regular Contributor
Active Commenter
Posts 20 Comments 30

Accepted as a Spotlight in ICLR2025!

submitted 13 days ago • 0 comments

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...

submitted 32 days ago • 1 comment

🔊 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

submitted 34 days ago • 2 comments

Very nice to see our work on LLM agent cooperation covered in Wired! www.wired.com/story/ai-soc...

submitted 48 days ago • 1 comment

Josh Tenenbaum on scaling up vs growing up and the path to human-like reasoning #NeurIPS2024

submitted 73 days ago • 2 comments

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!

submitted 74 days ago • 1 comment

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!

submitted 76 days ago • 0 comments

Come hang!

submitted 77 days ago • 0 comments

Now with a luma link: lu.ma/1bxqun5l

submitted 78 days ago • 0 comments

Only at NeurIPS

submitted 78 days ago • 2 comments

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!

submitted 83 days ago • 1 comment

Github Copilot output. A sad but fascinating alignment failure. Reveals hidden LLM biases by going out of their RLHF distribution

submitted 93 days ago • 3 comments

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/...

submitted 97 days ago • 3 comments

The computational cognitive science starter kit

submitted 99 days ago • 1 comment

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!)

submitted 103 days ago • 1 comment

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

submitted 107 days ago • 71 comments

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

submitted 107 days ago • 1 comment

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.

submitted 107 days ago • 1 comment

Many point to cumulative culture as the distinctive feature of human intelligence. Now, a new theory argues that our success comes from the way that cumulative culture is uniquely open-ended, i.e., we can accumulate novel technologies, languages, moral systems, or nearly anything

submitted 108 days ago • 1 comment

Many point to cumulative culture as the distinctive feature of human intelligence. Now, a new theory argues that our success comes from the way that cumulative culture is uniquely open-ended, i.e., we can accumulate novel technologies, languages, moral systems, or nearly anything adaptive.

submitted 108 days ago • 1 comment