OpenAI Podcast

OpenAI

Hosted by Andrew Mayne, The OpenAI Podcast features conversations with the people building with and working at OpenAI. Topics range from how new features are developed to what users are doing with the technology. It’s a practical look at how AI is made and where it’s going, told by the people closest to the work.

Hosted on Acast. See acast.com/privacy for more information.

Kategorie: Technologia

Słuchaj najnowszego odcinka:

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?