High Signal Podcasts Evidence ledger
Method
Browse
← Back to evidence

Evidence receipt / recommendation

Published · transcript-backed

Shawn Wang: recommendation

3 Nov 2023 Latent Space Beating GPT-4 with Open Source LLMs — with Michael Royzen of Phind

“I think we might want to give people an impression about like type of traffic that you have, because when you present it with a text box, you could type in anything.”

— Shawn Wang

Source trail

Everything needed to verify it.

Speaker
Shawn Wang
Attribution
Verified speaker
Claim type
recommendation
Recorded
3 Nov 2023
Publisher
Latent Space

Transcript context

…That was a great podcast, by the way. But yeah, so part of it is that people sometimes perhaps aren't even in an IDE. So like the whole task of software engineering goes way beyond just running code, right? There's also like a design stage. There's a planning stage. A lot of this happens like on whiteboards. It happens in notebooks. And so the web part also exists for that where you're not even coding it and you're just trying to get like a more conceptual understanding of what you're trying to build first. The podcast with Amman was great, but somewhere where I disagree with him is that you need to own the IDE. I think like he made some good points about not having platform risk in the long term. But some of the features that were mentioned like suggesting diffs, for example, those are all doable with an extension. We haven't yet seen with VS Code in particular any functionality that we'd like to do yet in the IDE that we can't either do through directly supported VS Code functionality or something that we kind of hack into there, which we've also done a fair bit of. And so I think it remains to be seen where that goes. But I think what we're looking to be is like we're not trying to just be in an IDE or be an IDE. Like Phind is a system that goes beyond the IDE and like is really meant to cover the entire lifecycle of a developer's thought process in going about like, hey, like I have this idea and I want to get from that idea to a working product. And so then that's what the long term vision of Phind is really about is starting with that. In the future, I think programming is just going to be really just the problem solving. Like you come up with an idea, you come up with like the basic design for the algorithm in your head, and you just tell the AI, hey, just like just do it, just make it work. And that's what we're building towards. I think we might want to give people an impression about like type of traffic that you have, because when you present it with a text box, you could type in anything. And I don't know if you have some mental categorization of like what are like the top three use cases that people tend to coalesce around. Yeah, that's a great question.…

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

Search evidence