Howard(Ziyu) Han retweeted
🚨 New Preprint! 🚨
Smarter LLMs are more selfish.
We show reasoning-enhanced models significantly prefer greed over cooperation. The more LLMs reason, the worse they cooperate.
👇 THREAD 👇
[Link to paper: arxiv.org/abs/2502.17720]
[1/n]
Howard(Ziyu) Han retweeted
🚨 New Paper! 🚨
"Groups that communicate diverse information make wiser decisions." Right? Not always—for LLMs, just like humans.
We bring this scrutiny to AI by adapting the Hidden Profile paradigm from social psychology to assess how multi-agent LLMs actually reason together.
👇 THREAD 👇
[Link to paper: arxiv.org/abs/2505.11556v1]
[1/n]
Excited to witness this special, timely and insightful work come out! Talk to John and Shixian, they are really cool.
John Zimmerman presenting at #CHI2025 Catch him and Ask about our AI Literacy paper — best paper honorable mention @meslami2
We thank @d19fe8 @koedinger @amyogan @HanZiyuh @du_yanlin for their feedback on this journey.
programs.sigchi.org/chi/2025…
Aloha🌴🏄#CHI2024! I will present my first CHI paper "Co-Designing Accessible Public Robots🤖" on Wednesday, May 15th, at 5:00 PM in room 321.
Join us if you are interested in how public robots can benefit from the engagement of people with mobility disabilities (PwMD)👩🦽. (1/3)
This work is a collective effort with @nikmartelaro, @perhaxis, @daraghbyrne, @Franklin_M_Li, and @aleresearches. We also appreciate the amazing ideas and conversations from our participants from both the mobility disability and Human-Robot Interaction communities. (3/3)
Howard(Ziyu) Han retweeted
If you're at @acmdis2023 this week, you have to check out @3llsaria's presentation tomorrow during the 4:30pm session. She'll about the impacts of algorithmic management on housekeeping, and workers' ideas on how to intervene.
