person · draft

Michael S. Bernstein

Stanford computer scientist who studies how computing shapes social behaviour and co-created generative agents, simulations of people built on language models; a co-founder of Simile.

Michael Bernstein teaches computer science at Stanford University, where he is also a senior fellow of the Institute for Human-Centered Artificial Intelligence.1,2 He studied Symbolic Systems at Stanford and took his master's and PhD in computer science at MIT.1 He designs social and interactive computing systems.1 One question his research asks is how modelling human attitudes and behaviour can help in crafting technology and social policy.1 His book Flash Teams (MIT Press) was a national bestseller, and he has received a Sloan Fellowship and the Computer History Museum's Tech for Humanity Prize.2

With Joon Sung Park, Percy Liang and others he built Social Simulacra, "creating populated prototypes for social computing systems" (UIST 2022), and generative agents, simulations he describes as the highest-cited research in the history of UIST.1 He is a co-founder of Simile, where he is chief data officer.1,3

On the wiki he is an author of Generative Agents and of Generative Agent Simulations of 1,000 People, and a founder of Simile.

affiliation
Stanford University
role
computer scientist
homepage
https://hci.stanford.edu/msb/

makes

  • Generative Agent Simulations of 1,000 People article draft

    Stanford-led study, 2024, revised 2026: agents built from two-hour interviews with 1,052 Americans predicted their survey answers at 83% of the people's own two-week retest consistency.

    open sourcerestricted data

  • Generative Agents (Smallville) tool draft

    Research code from Stanford for language-model characters that remember, reflect and plan, shown in Smallville, a small game town of 25 agents; a 2024 follow-up repository builds agents from interviews and survey answers and lets researchers put questions to them.

    open sourcepartly open dataopen participation

  • Simile tool draft

    Company founded by the Stanford researchers behind generative agents that sells simulations of how customers, employees or populations would respond to a change, from models it says are trained on data about real people.

    closed sourceclosed data

Tags: human-computer interaction, generative agents, social computing

staging: drafts and proposals shown