Political Battles at OpenAI, Safety vs. Capability in AI, Superalignment’s Death

May 18, 2024

Former OpenAI Chief Scientist Ilya Sutskever and Head of Alignment Jan Leike discuss the internal strife at OpenAI, focusing on the debate between safety and capability in AI development. They explore philosophical debates on AI capabilities, the establishment of a super alignment team, and the conflict within the organization leading to key departures.

Ask episode

Chapters

Transcript

Episode notes

Introduction

00:00 • 2min

Debate between Safety and Capability in AI Development

02:06 • 2min

Philosophical Debates on AI Capabilities and Safety at OpenAI

04:32 • 3min

Navigating Safety and Productivity in AI Research

07:17 • 5min

Debate on Safety vs. Capability in AI Development

11:54 • 3min