ไม่สามารถเล่นวิดีโอนี้
ขออภัยในความไม่สะดวก
Modeling Human Behavior with Generative Agents with Joon Sung Park - 632
ฝัง
- เผยแพร่เมื่อ 17 ส.ค. 2024
- Today we’re joined by Joon Sung Park, a PhD Student at Stanford University. Joon shares his passion for creating AI systems that can solve human problems and his work on the recent paper Generative Agents: Interactive Simulacra of Human Behavior, which showcases generative agents that exhibit believable human behavior. We discuss using empirical methods to study these systems and the conflicting papers on whether AI models have a worldview and common sense. Joon talks about the importance of context and environment in creating believable agent behavior and shares his team's work on scaling emerging community behaviors. He also dives into the importance of a long-term memory module in agents and the use of knowledge graphs in retrieving associative information. The goal, Joon explains, is to create something that people can enjoy and empower people, solving existing problems and challenges in the traditional HCI and AI field.
🔔 Subscribe to our channel for more great content just like this: th-cam.com/users/tw...
🗣️ CONNECT WITH US!
===============================
Subscribe to the TWIML AI Podcast: twimlai.com/po...
Join our Slack Community: twimlai.com/co...
Subscribe to our newsletter: twimlai.com/ne...
Want to get in touch? Send us a message: twimlai.com/co...
📖CHAPTERS
===============================
00:00:44 - Background
00:10:13 - Do Language Models Encode Human Behavior?
00:13:54 - Unpredictable AI Behaviors: What We're Learning
00:19:43 - Creating Believable Agents Through Emergent Behavior
00:27:48 - Studying Human Behavior: Small Groups vs. Large Collectives
00:31:46 - Exploring the Two Parts of Memory
00:42:39 - Retrieval Function Framework: Simplifying Complex Variables
00:49:47 - LLMs Bring Us Closer to Human-Like Agents
🔗 LINKS & RESOURCES
===============================
Paper: Generative Agents: Interactive Simulacra of Human Behavior - arxiv.org/abs/...
Paper: Evaluating Human-Language Model Interaction - arxiv.org/abs/...
For the complete resource list, head over to the show notes page: twimlai.com/go...
📸 Camera: amzn.to/3TQ3zsg
🎙️Microphone: amzn.to/3t5zXeV
🚦Lights: amzn.to/3TQlX49
🎛️ Audio Interface: amzn.to/3TVFAIq
🎚️ Stream Deck: amzn.to/3zzm7F5
#generativeai #aiagents #llm
Way back when there was only DOS, I had an AI psych analyst. I didn't even know what AI was, but it was good. I really enjoyed telling her my problems.
Yes was this Eliza?!?
Good podcast with great questions.
Thank for inspirational and intellectual content, as usual. One thing could improve: sound volume smart normalization. I mean sometimes it too loud (up to headache), sometimes it too silent (again up to headache). Maybe it's a feature of my head or maybe others bother as well. I sure exists smart filters for sound loudness normalization. Maybe microphones improving can help. I trying normalize sound loudness by myself and realize that I unable at this moment, so my hope for now that you can realize how to improve this.