Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
And, you know, you'd be in kind of in trouble, right? Well, if you're using neural networks to go and verify that your neural networks are safe and the hypothesis that you're testing for is like, okay, well, the neural network maybe isn't safe. And you have to worry about like, is there some way that it could be screwing with you? So, you know, I think that's not a big concern now.
0
💬
0
Comments
Log in to comment.
There are no comments yet.