Joon Sung Park
@joon-s-pk.bsky.social
CS Ph.D. student at Stanford. Oil painter. HCI, NLP, generative agents, human-centered AI
Pinned
Joon Sung Park
@joon-s-pk.bsky.social
· Nov 18
Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵
arxiv.org/abs/2411.10109
arxiv.org/abs/2411.10109
Reposted by Joon Sung Park
1000 people is a lot! You continue to impact us with agents-at-scale work, Joon.
Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵
arxiv.org/abs/2411.10109
arxiv.org/abs/2411.10109
November 19, 2024 at 2:10 AM
1000 people is a lot! You continue to impact us with agents-at-scale work, Joon.
Reposted by Joon Sung Park
Interesting new study! Heh, it makes me want to participate and see how well the agent replicates me. Would I be proud to get a lower score than average?
Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵
arxiv.org/abs/2411.10109
arxiv.org/abs/2411.10109
November 19, 2024 at 5:55 AM
Interesting new study! Heh, it makes me want to participate and see how well the agent replicates me. Would I be proud to get a lower score than average?
Reposted by 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 real answers!
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 real answers!
November 19, 2024 at 12:18 AM
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 real answers!
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 real answers!
Reposted by Joon Sung Park
So proud of this work with an amazing team!
Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵
arxiv.org/abs/2411.10109
arxiv.org/abs/2411.10109
November 18, 2024 at 5:24 PM
So proud of this work with an amazing team!
Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵
arxiv.org/abs/2411.10109
arxiv.org/abs/2411.10109
November 18, 2024 at 5:22 PM
Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵
arxiv.org/abs/2411.10109
arxiv.org/abs/2411.10109