Dario Amodei: belief

Transcript context

…So do you think RLHF makes the model smarter, or just appear smarter to the humans? I don’t think it makes the model smarter. I don’t think it just makes the model appear smarter. It’s like RLHF bridges the gap between the human and the model. I could have something really smart that can’t communicate at all. We all know people like this, people who are really smart but can’t understand what they’re saying. So I think RLHF just bridges that gap. I think it’s not the only kind of RL we do. It’s not the only kind of RL that will happen in the future. I think RL has the potential to make models smarter, to make them reason better, to make them operate better, to make them develop new skills even. And perhaps that could be done even in some cases with human feedback. But, the kind of RLHF we do today mostly doesn’t do that yet, although we’re very quickly starting to be able to. But if you look at the metric of helpfulness, it increases that?…

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