Max Kleiman-Weiner Profile
Max Kleiman-Weiner

@maxhkw

Followers
5K
Following
11K
Media
119
Statuses
897

professor @UW computational cognitive scientist working on social minds and machines. cofounder @CSM_ai. priors: PhD @MIT founder @diffeo (acquired)

Seattle, WA
Joined April 2011
Don't wanna be here? Send us removal request.
@Tianyi_Alex_Qiu
Tianyi Alex Qiu
8 days
🗺️ We started writing "AI Influence: Mechanisms, Amplifiers, and Consequences" at the start of 2025, when things weren't so out of hand. Later events - things like AI psychosis, coding agents - confirmed many of our worries. Check out our survey paper, and let's figure out a
1
5
10
@coop_ai
Cooperative AI Foundation
29 days
Watch our recent 'Evolving General Cooperation with a Bayesian Theory of Mind' seminar now on YouTube. Led by @maxhkw. Link below.
1
2
13
@coop_ai
Cooperative AI Foundation
1 month
How does a theory of mind enhance cooperation amongst agents? Don't miss our forthcoming seminar to explore this with @maxhkw ( @uw). Link below.
1
3
13
@kjha02
Kunal Jha
2 months
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! https://t.co/1t2fsW7jyL🧵
4
33
100
@maxhkw
Max Kleiman-Weiner
2 months
Great work led by @kjha02 and collaborators: @aydan_huang265, @EricYe29011995, @natashajaques! See his explainer thread: https://t.co/5KpFSfyeXW arXiv:
@kjha02
Kunal Jha
2 months
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! https://t.co/1t2fsW7jyL🧵
0
0
2
@maxhkw
Max Kleiman-Weiner
2 months
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? ROTE (Representing Others' Trajectories as Executables) treats behavior prediction as program synthesis.
4
1
10
@maxhkw
Max Kleiman-Weiner
2 months
When values collide, what do LLMs choose? In our new paper, "Generative Value Conflicts Reveal LLM Priorities," we generate value conflicts and find that models prioritize "protective" values in multiple-choice, but shift toward "personal" values when interacting.
@uilydna
Andy Liu
2 months
🚨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.
3
0
7
@jessi_cata
jessicat
2 months
Interesting work. Measuring intelligence without reference to specific goals is important (and relevant to alignment), and empowerment is one method. I have previously discussed theoretical intelligence measures by convergent instrumental achievements: https://t.co/tJYmOw4QD9
Tweet card summary image
lesswrong.com
It is analytically useful to define intelligence in the context of AGI. One intuitive notion is epistemology: an agent's intelligence is how good its…
@jinyeop_song
Jinyeop Song
2 months
#1. New paper alert!🚀 How do we evaluate LM agents today? Mostly benchmarks. But: (1) good benchmarks are costly + labor-intensive, and (2) they target narrow end goals, missing unintended capabilities. In our recent paper, we propose a goal-agnostic alternative for evaluating
0
1
15
@jinyeop_song
Jinyeop Song
2 months
#1. New paper alert!🚀 How do we evaluate LM agents today? Mostly benchmarks. But: (1) good benchmarks are costly + labor-intensive, and (2) they target narrow end goals, missing unintended capabilities. In our recent paper, we propose a goal-agnostic alternative for evaluating
1
4
26
@maxhkw
Max Kleiman-Weiner
2 months
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. Led by @jinyeop_song! 🧵👇
@jinyeop_song
Jinyeop Song
2 months
#1. New paper alert!🚀 How do we evaluate LM agents today? Mostly benchmarks. But: (1) good benchmarks are costly + labor-intensive, and (2) they target narrow end goals, missing unintended capabilities. In our recent paper, we propose a goal-agnostic alternative for evaluating
1
0
6
@maxhkw
Max Kleiman-Weiner
2 months
Could humans and AI become a new evolutionary individual?
Tweet card summary image
pnas.org
Could humans and AI become a new evolutionary individual?
0
0
4
@maxhkw
Max Kleiman-Weiner
2 months
Excited to work with the Cooperative AI Foundation on multi-agent safety, mitigating gradual disempowerment, and AI for human cooperation! Consider applying for this 3 month research fellowship ⬇️
@AI_Safety_SA
AI Safety South Africa
3 months
🌍 Join a cohort of ambitious researchers in Cape Town for a cooperative AI research fellowship Spend 3 months researching the biggest problems in cooperative AI, with world-class mentorship from Google DeepMind, Oxford, and MIT researchers. See comments for details!
0
0
9
@miniapeur
Mathieu
3 months
14
137
1K
@CSM_ai
Common Sense Machines
3 months
CSM Cube delivers industry-leading model quality, topology, parts, and AI re-topology, providing a significant advantage for workflows from quick prototypes to full production.
38
88
918
@IJCAIconf
IJCAIconf
3 months
#Workshop Generative AI & Theory of Mind in Communicating Agents #InvitedTalk 🗣️Joyce Y. Chai @UMich 🗣️Tomer Ullman @TomerUllman @Harvard 🗣️Vered Swartz @UBC & @VectorInst 🗣️Max Kleiman-Weiner @maxhkw @UW 🗣️Pei Zhou @peizNLP @Microsoft #IJCAI2025 https://t.co/YLGuc3sKYK
1
2
4
@seregavr
Sergey Gavrilets
4 months
The evolution of zero-sum and positive-sum worldviews https://t.co/vgcpuKkM1H
2
23
77
@maxhkw
Max Kleiman-Weiner
4 months
Quantifying the cooperative advantage shows why humans, the most sophisticated cooperators, also have the most sophisticated machinery for understanding the minds of others and offers principles for building more cooperative AI systems. Full paper:
Tweet card summary image
pnas.org
Theories of the evolution of cooperation through reciprocity explain how unrelated self-interested individuals can accomplish more together than th...
1
0
6