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

The Obfiscated Arguments Problem

The dishonest debater can construct arguments such that finding the flaow in them is intractable, but that they appear to support the dishonest answer. It doesn't have to look like some sort of crpto i thing where you 're asking for a known commutation in tractable thing. The obtimal tragedy sometimes being combination an tragible. We cant efficiently determine whether or not numbers or promaly tell you the factors? Yes, yes.

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