The Logan Bartlett Show cover image

EP 63: Eliezer Yudkowsky (AI Safety Expert) Explains How AI Could Destroy Humanity

The Logan Bartlett Show

CHAPTER

The Hard Problem With Alignment

So can you put a fine point on why alignment is such a hard problem to solve it sounds like there's infinite permutations or things that you actually can't determine if they're correct or not. In fact you're example of making a secure operating system you don't actually know. And then well no people are just overly optimistic about whether or not they've solved itYou can know whether a system is secure or not. So sort of. Okay that's fair. We cannot verify the most important things that we would like an AI to do. If we could we could just like verify all its actions in the first place. Like yeah like the verifier is broken.

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.
App store bannerPlay store banner