This Day in AI Podcast cover image

Aligning Super Intelligence & The Open Web's Uncertain Future + GPT-4 General Availability | EP22

This Day in AI Podcast

00:00

How to Stop a Super Intelligence From Making Things Even More Intelligent

"I hate alignment stop aligning stuff. But you're talking about creating a super intelligence and then having a presumably less powerful thing control that super intelligence right because like the alignment can't be more powerful than the super intelligence or the alignment is the super intelligence therefore, it must be less powerful," he says. "How's that going to work I don't get it." He continues: "It seems futile to me ... Like do they really think in the long run they're going to be able to control it if it's more intelligent than us?"

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