13 - First Principles of AGI Safety with Richard Ngo
AXRP - the AI X-risk Research Podcast
00:00
Is There a Limit to Human Intelligence?
Humans have a strong advantage at expanding to new areas and gathering resources. We're not very specialized at things like doing mathematical research, reasoning about a alignment. And so it seems very plausible to me that as we train our eyes to become increasingly general and generally intelligent, you know, eventually they are going to surpass humans at all these things. But the hope would be that they surpass humans at the types of things that are most useful and least worryinga before they surpass us in other ways.
Transcript
Play full episode
