Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
And the linear representation hypothesis is, you could sort of think of it roughly as saying that that's actually kind of the fundamental thing that's going on, that everything is just different directions have meanings, and adding different direction vectors together can represent concepts. And the Mikhailov paper sort of took that idea seriously.
0
💬
0
Comments
Log in to comment.
There are no comments yet.