Dario Amodei: belief

Transcript context

…… or it’s tending that way. Trying to. I mean, I think we’re still early in terms of our ability to see things, but I’ve been surprised at how much we’ve been able to look inside these systems and understand what we see. Unlike with the scaling laws where it feels like there’s some law that’s driving these models to perform better, on the inside, the models aren’t… There’s no reason why they should be designed for us to understand them, right? They’re designed to operate, they’re designed to work. Just like the human brain or human biochemistry. They’re not designed for a human to open up the hatch, look inside and understand them. But we have found, and you can talk in much more detail about this to Chris, that when we open them up, when we do look inside them, we find things that are surprisingly interesting. And as a side effect, you also get to see the beauty of these models. You get to explore the beautiful nature of large neural networks through the MEC and TERP kind of methodology.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.