🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

This is groundbreaking, super exciting work!

How close can LM agents simulate people? We interview person P for 2 hours and prompt an LM with the transcript, yielding an agent P'. We find that P and P' behave similarly on a number of surveys and experiments. Very excited about the applications; this also forces us to think

In a follow-up to the generative agents paper, Joon Sung Park+team demonstrate that anchoring agents in rich qualitative information about an individual enables simulations to replicate an individual's attitudes 85% as well as the individual replicates themselves, + reduces bias

So thrilled to share our work on this~! Grounding generative agents in real, verifiable behavior is the step that takes this method from producing simulacra to creating simulations that capture the richness of human experiences.

Excited to share this new work that shares a new method for creating realistic generative agents that can be used for synthetic social science. Such a pleasure to work with lead author Joon Sung Park

Crazy interesting paper in many ways: 1) Voice-enabled GPT-4o conducted 2 hour interviews of 1,052 people 2) GPT-4o agents were given the transcripts & prompted to simulate the people 3) The agents were given surveys & tasks. They achieved 85% accuracy in simulating interviewees

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!🧵⬇️

Book announcement: with Melissa Valentine, we are publishing "Flash Teams: Leading the Future of AI-Enhanced, On-Demand Work." It's a leadership book synthesizing a decade of Stanford University research on how computing, online platforms, and AI reshape teamwork. Coming October from The MIT Press @mitpress.bsky.social!

Todo lists, docs, email style – if you've got individual or team knowledge you want ChatGPT/Claude to have access to, Knoll (knollapp.com) is a personal RAG store from Stanford University that you can add any knowledge into. Instead of copy-pasting into your prompt every time,

📢 New policy brief: AI agents that can simulate human behaviors and attitudes can help test ideas in social science. Our latest brief introduces a generative AI agent architecture that simulates the attitudes of 1,000+ real people. Learn more: hai.stanford.edu/policy/simulat…

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. 🧵