Evidence receipt / commitment
Published · transcript-backedAman Sanger: commitment
22 Aug 2023 Latent Space Cursor.so: The AI-first Code Editor — with Aman Sanger of Anysphere
“It's called Priompt. And we built this because we didn't really find a good way of solving for the problem of when you have a variable number of kind of inputs that you want to stuff into the prompt and you have like a fixed length prompt, right?”
Source trail
Everything needed to verify it.
- Speaker
- Aman Sanger
- Attribution
- Verified speaker
- Claim type
- commitment
- Recorded
- 22 Aug 2023
- Publisher
- Latent Space
Transcript context
…Cool. And then maybe to sketch out a little bit more about the company and then we'll zoom out to just general LLM observations. You're also working on a prompt tooling thing called Priompt? Yeah. So this is just an internal tool that we use. It's called Priompt. And we built this because we didn't really find a good way of solving for the problem of when you have a variable number of kind of inputs that you want to stuff into the prompt and you have like a fixed length prompt, right? You can only use 4096 tokens. How do you encode for rules and how to properly kind of order the inputs that go into it? And Priompt or priority prompting are intermediary solution for this, where you can kind of encode very custom rules into how you build up the prompt based on how, I guess, overflowing it is, right? So let's say I have a bunch of previous chat messages and then I also have the code from the current file. So maybe what you want to do is you want some rules where if everything can fit in, you put it all in. But then you start by like first removing like all the old chat messages. Then once it gets to a certain length, you don't want to remove any more chat messages and you want to start removing parts of the file. And then you want to remove parts of the file in this particular truncation strategy, which tends to work quite well. So this kind of thing where like as you kind of slide the window and how many tokens you're allotted, you can see like the prompt is like very, very differently constructed. So it's like optimal kind of at all sizings. And we found that quite helpful internally. 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?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.