AI Safety Fundamentals: Alignment cover image

AI Safety via Debate

AI Safety Fundamentals: Alignment

CHAPTER

The Utility of Debate in AI Alignment

The utility of debate is an approach for AI alignment rests on the following central claim. In the debate game it is harder to lie than to refute a lie. It is possible to find approximate Nash equilibria with some version of gradient descent such as a self play algorithm similar to silver at L 2017 B. We will initially consider a question answering setting, though section 2.3 covers other settings, including environment interaction.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner