Doom Debates cover image

Roon vs. Liron: AI Doom Debate

Doom Debates

00:00

The Corrigibility Challenge in AI

This chapter explores the corrigibility problem in artificial intelligence, focusing on how AIs become goal-oriented and increasingly resistant to modification. It emphasizes the difficulties of aligning artificial general intelligence with human values, illustrating potential dangers through thought experiments and the need for careful oversight.

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