LessWrong (Curated & Popular) cover image

[HUMAN VOICE] "Updatelessness doesn't solve most problems" by Martín Soto

LessWrong (Curated & Popular)

00:00

Exploring the Impact of Updateful and Updateless Agents in Various Scenarios

Exploring the diverse decision theories and generalization in AI training for updateful and updateless agents across various scenarios, highlighting the complexity of super-intelligent interactions and the potential lack of convergence in updatelessness levels.

Play episode from 22:13
Transcript

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