AXRP - the AI X-risk Research Podcast cover image

6 - Debate and Imitative Generalization with Beth Barnes

AXRP - the AI X-risk Research Podcast

00:00

Is There a Penalty for Choosing What Recurses On?

If you just let the human choose which thing to focus on, then they'd just be guessing every time. The magic that's coming in here is being able to use the debater's knowledge of wether mistake is rather than just having the human guessing. Yet, the reason you need this blak penalty for choosing what to recurse on, is yet, we're just as worried about the dishonest debater being able to force a draw as being able to win. Cause if your debates just like drawer all the time, just this is unusable.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app