Believability in AI
Joon discusses the empirical approach to understanding how generative agents can mimic believable human behavior. He highlights the importance of evaluating AI systems, like machine vision, in real-world applications, particularly for assisting individuals with disabilities. The conversation delves into the challenges of measuring believability in AI interactions, drawing parallels to simulations like the Sims, and exploring how these agents can reflect human societal dynamics.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Modeling Human Behavior with Generative Agents with Joon Sung Park - 632
Related Questions