Lex Fridman: belief

Transcript context

…I’m amazed at how clean it’s been. I’m amazed at things like induction heads. I’m amazed at things like that we can use sparse auto-encoders to find these directions within the networks, and that the directions correspond to these very clear concepts. We demonstrated this a bit with the Golden Gate Bridge Claude. So this was an experiment where we found a direction inside one of the neural networks layers that corresponded to the Golden Gate Bridge. And we just turned that way up. And so we released this model as a demo, it was kind of half a joke, for a couple days, but it was illustrative of the method we developed. And you could take the model, you could ask it about anything. It would be like you could say, “How was your day?” And anything you asked, because this feature was activated, it would connect to the Golden Gate Bridge. So it would say, I’m feeling relaxed and expansive, much like the arches of the Golden Gate Bridge, or- It would masterfully change topic to the Golden Gate Bridge and integrate it. There was also a sadness to the focus it had on the Golden Gate Bridge. I think people quickly fell in love with it, I think. So people already miss it, because it was taken down, I think after a day. Somehow these interventions on the model, where you kind of adjust its behavior, somehow emotionally made it seem more human than any other version of the model.…

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