Evidence receipt / evaluation
Published · transcript-backedMichael Royzen: evaluation
3 Nov 2023 Latent Space Beating GPT-4 with Open Source LLMs — with Michael Royzen of Phind
“Even GPT, like the text DaVinci 2 was available at the time, wasn't that good at generating code and it would generate like very, very short, very incomplete code snippets. And so we launched that last summer, got some traction, but really like we were only doing like, I don't know, maybe like 10,000 searches a day.”
Source trail
Everything needed to verify it.
- Speaker
- Michael Royzen
- Attribution
- Verified speaker
- Claim type
- evaluation
- Recorded
- 3 Nov 2023
- Publisher
- Latent Space
Transcript context
…Cool. So Bing web search, and then August you launched V2. Is V2 the Phind as a system pitch? Or have you moved, evolved since then? Yeah, so I don't, like the V2 moniker, like, I don't really think of it that way in my mind. There's like, there's the version we launched during, last summer during YC, which was the Bing version directed towards programmers. And that's kind of like, that's why I call it like the first incarnation of what we currently are. Because it was already directed towards programmers. We had like a code snippet search built in as well, because at the time, you know, the models we were using weren't good enough to generate code snippets. Even GPT, like the text DaVinci 2 was available at the time, wasn't that good at generating code and it would generate like very, very short, very incomplete code snippets. And so we launched that last summer, got some traction, but really like we were only doing like, I don't know, maybe like 10,000 searches a day. Some people knew about it.…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.