Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
But you could imagine all kinds of ways in which you might map words to vectors. But it seems like when we train neural networks, they like to go and map words to vectors such that they're sort of linear structure in a particular sense, which is that directions have meaning.
0
💬
0
Comments
Log in to comment.
There are no comments yet.