Scott Wu: belief

Transcript context

…Okay. Is that a good example? Oh, there it is. What a beautiful website for my newsletter. Is that just a good example of the kind of thing Devin is very good at like, "Here's a very specific thing to change on the website"? How does your people think about what Devin is very good at and maybe where it starts to fall apart? The way that we often describe it is, I think, Devin is best when it is working on tasks that are well-defined. One way to put it, you might... On tasks that are well-defined. One way to put it is, you want to be giving Devin tasks, not problems. And a lot of these things like what you just saw, which was kind of like a quick front-end feature request or a bug fix or adding testing and documentation or things like that. One of the things that makes a loop really nice obviously is a quick way to iterate and test. And so with something like this, obviously super easy for us, for example, to just go pull up the preview and see that the link worked. Obviously it would be easy for Devin to do as well. Devin will often go and log in to Devin and start a Devin session and make sure when it's working on our code base, which is kind of hilarious. But yeah, you generally want something that is kind of easy to verify and easy to test is the main thing. And you can work on bigger projects or bigger asks as well, obviously. But in that case you should certainly expect to need to steer Devin more to make sure it's going the right direction. It's interesting because that's very similar to the way people talk about synthetic data and reinforcement learning, creating data that's very easy. There's a very definitive answer, yes and no.…

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