Lightnews — Scholar-powered news

Reposted by Max Kleiman-Weiner

Kunal Jha @kjha02.bsky.social · 5d

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

Max Kleiman-Weiner @maxkw.bsky.social · 5d

arXiv: arxiv.org/abs/2510.01272

Modeling Others' Minds as Code

Accurate prediction of human behavior is essential for robust and safe human-AI collaboration. However, existing approaches for modeling people are often data-hungry and brittle because they either ma...

arxiv.org

3

Max Kleiman-Weiner @maxkw.bsky.social · 5d

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.

2 2 14

Max Kleiman-Weiner @maxkw.bsky.social · 6d

Definitely, we should look closer at sample complexity for training but for things like webnav there are massive datasets so could be good fit.

1

Max Kleiman-Weiner @maxkw.bsky.social · 6d

In some sense, yes, in that you need diverse trajectories of the agent's behavior in different contexts, but you don't need to have access to those goals, or even the distribution, and the agent might be doing non-goal-directed behavior, such as exploration.

1 1

Max Kleiman-Weiner @maxkw.bsky.social · 6d

Great work led by @andyliu.bsky.social and collaborators:
@kghate.bsky.social, @monadiab77.bsky.social, @daniel-fried.bsky.social, @atoosakz.bsky.social
Preprint: www.arxiv.org/abs/2509.25369

Generative Value Conflicts Reveal LLM Priorities

Past work seeks to align large language model (LLM)-based assistants with a target set of values, but such assistants are frequently forced to make tradeoffs between values when deployed. In response ...

www.arxiv.org

2

Max Kleiman-Weiner @maxkw.bsky.social · 6d

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.

Andy Liu @andyliu.bsky.social · 6d

🚨New Paper: LLM developers aim to align models with values like helpfulness or harmlessness. But when these conflict, which values do models choose to support? We introduce ConflictScope, a fully-automated evaluation pipeline that reveals how models rank values under conflict.
(📷 xkcd)

1 9

Max Kleiman-Weiner @maxkw.bsky.social · 6d

Very cool! Thanks for sharing! Would be interesting to compare your exploration ideas on open ended tasks beyond little alchemy with EELMA

1

Max Kleiman-Weiner @maxkw.bsky.social · 7d

Work led by Jinyeop Song together with Jeff Gore. Check out the preprint here: arxiv.org/abs/2509.22504

Estimating the Empowerment of Language Model Agents

As language model (LM) agents become more capable and gain broader access to real-world tools, there is a growing need for scalable evaluation frameworks of agentic capability. However, conventional b...

arxiv.org

5

Max Kleiman-Weiner @maxkw.bsky.social · 7d

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.

3 2 16

Max Kleiman-Weiner @maxkw.bsky.social · Aug 6

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)!

Claire Yang @claireyang.bsky.social · Aug 6

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"

7

Reposted by Max Kleiman-Weiner

Claire Yang @claireyang.bsky.social · Aug 6

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!

3 15

Max Kleiman-Weiner @maxkw.bsky.social · Jul 31

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

2

Reposted by Max Kleiman-Weiner

samuel mehr @mehr.nz · Jul 31

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