Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
And so, you know, the project of mechanistic interoperability is to somehow figure out how do these weights correspond to algorithms. Um, and in order to do that, you also have to understand the activations because it's sort of the activations are like the memory. And if you, if you imagine reverse engineering a computer program, um, and you have the binary instructions, you know,
0
💬
0
Comments
Log in to comment.
There are no comments yet.