Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
Lex Fridman
And we should say this example of the field of mechanistic interpretability is just a rigorous, non-hand wavy way of doing AI safety. Yes. Or it's tending that way.
0
💬
0
Comments
Log in to comment.
There are no comments yet.