Noam Shazeer: belief

Transcript context

…I mean, I think having the system explore algorithmic research ideas seems like something where there's still a human in charge of that. Like, it's exploring the space, and then it's going to, like, get a bunch of results, and we're going to make a decision, like, are we going to incorporate this particular, you know, learning algorithm or change to the system into kind of the core code base? And so I think you can put in safeguards like that that enable us to get the benefits of the system that can sort of improve or kind of self-improve with human oversight, uh, without necessarily letting the system go full-on self-improving without any any notion of a person looking at what it's doing, right? That's the kind of engineering safeguards I'm talking about, where you want to be kind of looking at the characteristics of the systems you're deploying, not deploy ones that are harmful by some measures and some ways, and you have an understanding of what its capabilities are and what it's likely to do in certain scenarios. So, you know, I think it's not an easy problem by any means, but I do think it is possible to make these these systems safe. Yeah. I mean, I think we are also going to use these systems a lot to check themselves, check other systems. Even as a human, it is easier to recognize something than to generate it. One thing I would say is if you expose the model's capabilities through an API or through a user interface that people interact with, I think then you have a level of control to understand how is it being used and put some boundaries on what it can do. And that I think is one of the tools in the arsenal of how do you make sure that what it's going to do is sort of acceptable by some set of standards you've set out in your mind?…

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