Public evidence record
Published podcast speaker
Claim ledger
15 transcript-backed records
01 / belief
“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.”
02 / belief
“Specifically, I think just being generalist at code, where before you had these specialized models, right, where codex was supposed to be kind of specialized for code.”
03 / belief
“We learned this from CAD, and we strongly believe this now that it is much better to be a user of the product you're building.”
04 / belief
“We think there's a lot of interesting work that we're doing that's left to be done.”
05 / belief
“If you have a really, really rigorous set of tests where you can completely confirm whether or not the agent has done the right thing, I think that solves it.”
06 / uncertainty
“I don't know how far you can take the agent stuff with a four level model, but I think with like a 4.”
07 / belief
“I think the issues we want to use for sparingly because of how expensive it is and 3.”
08 / evaluation
“We found that it was not just good at creating net new things, but refactoring code, editing code, helping you debug kind of every single aspect of software development felt so different with these models.”
09 / recommendation
“I think if we want to do things where the agent takes many... So for the Code Interpreter style thing, the great thing is because you're breaking it down to these units, you can kind of batch together a bunch of commands at each step, just kind of ask the user because they're always kind of watching.”
10 / preference
“I do think like in terms of inline edits, which means inside the editor, you can press command K in Cursor and then ask for some kind of modification of the code or ask for a generation of the code. And I do think we have probably the best UX for that because if you look at what someone like Sourcegraph does, I mean, Sourcegraph code is a great product, but they basically have to use the GitHub pull request comment feature in order to do it.”
11 / prediction
“I think I have some thoughts on this because there's the whole thing with chinchilla scaling and then people are now saying, oh, chinchilla scaling doesn't matter because of inference.”
12 / evaluation
“I've been meaning to do it at some point, but there's this paper called Babel code and they have a library which I think literally translates human eval into all other languages. And I think that would be a really good test because the other issues, a lot of the models that perform really well on human eval are pure Python, right?”
13 / commitment
“Now I think I'll go on runs and if someone tries passing me, I won't let it happen.”
14 / recommendation
“5 would strongly recommend using the Azure model because there you get access to completions, meaning you can put kind of words in GPT 3.”
15 / commitment
“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?”