Dwarkesh Patel: belief

Transcript context

…I think the good news is that analyzing text seems to be easier than generating text. So I believe that the ability of language models to actually analyze language model output and figure out what is problematic or dangerous will actually be the solution to a lot of these control issues. We are definitely working on this stuff. We've got a bunch of brilliant folks at Google working on this now. And I think it's just going to be more and more important, both from a “do something good for people” standpoint, but also from a business standpoint, that you are, a lot of the time, limited in what you can deploy based on keeping things safe. And so it becomes very, very important to be really, really good at that. Yeah, obviously, I know you guys take the potential benefits and costs here seriously, and it's truly remarkable. I know you guys get credit for it, but not enough. I think there's just, there are so many different applications that you have put out for using these models to make the different areas you talked about better. Um, but I do think that… again, if you have a situation where plausibly there's some feedback loop process, on the other end, you have a model that is as good as Noam Shazeer, as good as Jeff Dean. If there's an evil version of you running around, and suppose there's a million of them, I think that's really, really bad. That could be much, much worse than any other risk, maybe short of nuclear war or something. Just think about it, like a million evil Jeff Deans or something. Where do we get the training data?…

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