Connor Leahy on the State of AI and Alignment Research
Future of Life Institute Podcast
The Importance of Alignment in Artificial Intelligence
I do not expect that if I had an unaligned existential risk AGI and I did the chat GPT equivalent to it, that saves you. That gives you nothing. No part of this addresses this problem. It's like you can play shell games with where the difficulty is until you confuse yourself sufficiently to thinking it's fine. This is a very common thing. How does the science all the time? Especially in cryptography, there's the saying everyone can create a code complex enough that they themselves can break it. And this is a similar thing here where everybody can create a alignment scheme sufficiently complicated that they themselves think it's safe. But so what? Like, if you just confuse where
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
