New paper: Do social media algorithms shape affective polarization? We ran a field experiment on X/Twitter (N=1,256) using LLMs to rerank content in real-time, adjusting exposure to polarizing posts. Result: Algorithmic ranking impacts feelings toward the political outgroup!🧵⬇️

People like to talk as it's easy and natural. Now that there are Large *Audio* Models 🔊, which model do users like the most? Introducing Talk Arena🎤: an open platform where users speak to LAMs and receive text responses. Through open interaction, we focus on rankings based on

LM agents today primarily aim to automate tasks. Can we turn them into collaborative teammates? Introducing Collaborative Gym (Co-Gym), a framework for enabling & evaluating human-agent collaboration! I now get used to agents proactively seeking confirmation or my deep thinking.

Check out 🔥 EgoNormia: a benchmark for physical social norm understanding egonormia.org Can we really trust VLMs to make decisions that align with human norms? 👩‍⚖️ With EgoNormia, a 1800 ego-centric video 🥽 QA benchmark, we show that this is surprisingly challenging

Trust me, try it out - it’s incredibly useful!!

What if LLMs could learn your habits and preferences well enough (across any context!) to anticipate your needs? In a new paper, we present the General User Model (GUM): a model of you built from just your everyday computer use. 🧵

New #ACL2025NLP Paper! 🎉 Curious what AI thinks about YOU? We interact with AI every day, offering all kinds of feedback, both implicit ✏️ and explicit 👍.  What if we used this feedback to personalize your AI assistant to you? Introducing SynthesizeMe! An approach for

🚨 70 million US workers are about to face their biggest workplace transmission due to AI agents. But nobody asks them what they want. While AI races to automate everything, we took a different approach: auditing what workers want vs. what AI can do across the US workforce.🧵

The rise of AI Companion and how it affects well-being 🤔 Check out work below from Yutong Zhang Dora Zhao 👇 🤖People with less offline support are more likely to seek companionship from AI 🤖 General interaction links to greater well-being, but seeking companionship is tied

There’s a lot of speculation around how AI will change human relationships. To dig into this question, we collect surveys from 1000+ Character.AI users and 400,000+ messages to analyze the relationship between AI companionship and well-being. Preprint:

Chatbot companions are going to be our society's next moral panic, I suspect. Work by Yutong Zhang suggests that people turn to them especially when they lack outside social support.

Are AI scientists already better than human researchers? We recruited 43 PhD students to spend 3 months executing research ideas proposed by an LLM agent vs human experts. Main finding: LLM ideas result in worse projects than human ideas.

Thank you to everyone for your energy and enthusiasm in joining this adventure with me so far!