Aman Sanger: belief

Transcript context

…And you chose the JSX approach. I'm not going to ask you too much about like design choice. I mean, it's popular with React. Fixies also put out AI JSX. Do you find that like helpful? Do you think that like some kind of DSL might emerge for prompting? Yeah, I think it's still pretty early. And it's not clear what the best way to do. I think for very lightweight, easy prompting, like you should just use strings. When you're doing kind of prompt engineering, and really like rigorous prompt construction where you can have a bunch of different possible inputs in the prompt. We think JSX makes a lot of sense. It's because it's kind of like website development where you'll have different kind of screen sizes, different kinds of devices that can look at it. And in a similar way, you've different kinds of prompts, right? You've different prompt context lengths. And you basically want across all different context lengths to get a very, very good prompt for the model. And so yeah, that's why I think like JSX kind of makes sense. It's not clear if it is like the best way of doing it. I think the jury's still out on that. One way to deal with the context length model issue is to train your own model that has a very long context length, like magic.dev, which announced a 5 million context length window. I don't know how credible that is. I haven't tried it. But your thoughts?…

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