World Models Podcast Summaries
World Models on Yedapo: 3 summarized podcast and YouTube episodes. Each includes key takeaways, core concepts and notable quotes with timestamps.
AMD CEO Lisa Su Live on TBPN | Oliver Cameron, Mohammad Norouzi, Anjney Midha, Lisa Su
TBPN
Jul 23, 2026
This episode explores AMD's strategic push into the AI hardware market, featuring insights on world models, infrastructure bottlenecks, and the shift toward output-maxing efficiency. Industry leaders discuss the critical need for energy capacity and the evolving role of AI in physical and virtual systems.
Key insight: Only 15% of data center compute capacity in the United States is currently being utilized, representing a massive national security and economic efficiency crisis.
World Models, JEPA And The Path To Sample-Efficient RL
Y Combinator
Jul 17, 2026
The hosts argue that current AI models fail at sample efficiency because they lack an explicit 'world model' to simulate consequences before acting. By integrating world models—which predict future states and actions—with reinforcement learning, researchers are moving beyond simple pattern matching toward systems that can plan, adapt, and learn from minimal data, much like the human brain.
Key insight: A 1967 study showed that people who only imagined performing basketball layups improved their accuracy by 23%, nearly matching the 24% improvement of those who physically practiced, proving the immense power of the human brain's internal world model.
Nobody gets this right
David Shapiro
Jun 7, 2026
The host argues that the distinction between language models and world models is a false dichotomy rooted in category errors. He asserts that all sensory data can be tokenized and predicted, meaning future 'omni-models' will naturally unify abstract reasoning with physical intuition, rendering current debates about 'real-world' versus 'word-based' AI largely obsolete.
Key insight: Prediction is prediction; whether an AI is navigating physical space or solving abstract math, the underlying mechanism of tokenizing and predicting sequences remains the most effective method for achieving general intelligence.