About this episode
The episode discusses the Model Spec, a framework defining AI model behavior, featuring insights from OpenAI researcher Jason Wolfe.
The more AI can do, the more we need to ask what it should and shouldn’t do. In this episode, OpenAI researcher Jason Wolfe joins host Andrew Mayne to talk about the Model Spec, the public framework that defines intended model behavior. They discuss how the Model Spec works in practice, including how the chain of command handles conflicts between instructions, and how OpenAI evolves it based on feedback, real-world use, and new model capabilities. Chapters 00:00 Introduction 01:10 What is the Model Spec? 03:55 How does the Model Spec work in practice? 06:26 Transparency: Where to read the Model Spec & give feedback 07:51 How did the Model Spec originate? 10:02 How does the spec translate into model behavior? 11:26 What is the hierarchy / chain of command? 13:35 Handling edge cases like Santa Claus 17:41 How does the Model Spec evolve over time? 19:59 What happens when models disagree with the spec? 22:05 How do smaller models follow the spec? 23:16 Is chain-of-thought useful for alignment? 24:16 Model Spec vs Anthropic’s Constitution 26:28 What surprised you most? 26:56 How do you define the scope of the spec? 27:44 What is the future of the Model Spec? 31:16 How should…
People in this episode
Host: Andrew Mayne
Guest: Jason Wolfe
Topics covered
- AI ethics
- Model Spec
- model behavior
- transparency
- AI alignment
Keywords
- Model Spec
- AI behavior
- transparency
- feedback
- alignment
Mentioned in this episode
Organizations: OpenAI
More episodes of OpenAI Podcast
- How a reasoning model cracked an 80-year-old math problem - Episode 20 · June 4, 2026 · 41 min
- Inside image generation’s Renaissance moment - Episode 19 · May 14, 2026 · 29 min
- Why AI needs a new kind of supercomputer network - Episode 18 · May 6, 2026 · 38 min
- What happens now that AI is good at math? - Episode 17 · April 28, 2026 · 43 min
- Building AI for Life Sciences - Episode 16 · April 16, 2026 · 44 min
- Building AI for better healthcare - Episode 14 · March 16, 2026 · 31 min
Explore listener stats, chart rankings, contacts and more on the OpenAI Podcast podcast page.