AXRP - the AI X-risk Research Podcast cover image

10 - AI's Future and Impacts with Katja Grace

AXRP - the AI X-risk Research Podcast

00:00

Is There a Better Model for Incoherent Preferences?

i've been thinking of it as like, well, you have indifferent coves across different sets of things you could have. And if you have incoherent preferences in this way, it's sot of like you have two different sets of indifferenc cuves and they just lik, cross and hit each other. It seems ike an practice. If you look at humans, say, i think they do become orcoherent of a time, like they do figure out the logical implications of some things that they like,. But vi nicet to have a clearer model of it. So i guess i've been thinking about what is a better model for incoherent preferences.

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