The Reasoning Revolution

OpenAI's o1 and o3 aren't just better language mo…

An episode of the NeurIPS 2025 by Basis Set podcast, hosted by Basis Set, titled "The Reasoning Revolution" was published on November 27, 2025 and runs 12 minutes.

November 27, 2025 ·12m · NeurIPS 2025 by Basis Set

Summary

OpenAI's o1 and o3 aren't just better language models—they actually think. You'll learn how reinforcement learning creates genuine reasoning capabilities, but also discover the dark side: "mode collapse" creates an artificial hivemind where models converge to eerily similar responses. The uncomfortable truth? Even the best RL refines existing knowledge rather than discovering new concepts, and there's a 1000x gap in data efficiency between AI and human brains. This episode cuts through the hype around reasoning models to show you what's real and what's still missing. Topics Covered - Large Reasoning Models (LRMs) vs. traditional LLMs - Reinforcement learning mechanics (explained accessibly) - The mode collapse problem (AI converging to similar responses) - Data scaling wall and synthetic data challenges - Why small models (32B parameters) are rising in importance - The verification crisis in AI deployment

Episode Description