Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
And then there's been some other papers suggesting that maybe in very small models, you get nonlinear representations. I think that the jury's still out on that. But I think everything that we've seen so far has been consistent with the linear representation hypothesis. And that's wild. It doesn't have to be that way.
0
💬
0
Comments
Log in to comment.
There are no comments yet.