Public evidence record
Published podcast speaker
Books, apps, and tools
tool / uses
“I used Google Code Search while I was an intern. And then after I left that internship and worked elsewhere, it was the single dev tool that I missed the most. I felt like my job was just a lot more tedious and much more of a hassle without it.”
app / uses
“Like we run Starcoder on top of Fireworks and that's made it so that we just don't have to think about building up an inference stack. And so that's great for us because it allows us to focus more on the kind of like data fetching, the knowledge graph and model fine tuning, which we've also invested a bit in.”
Claim ledger
13 transcript-backed records
01 / belief
“I think the critique of LSP from a Kythe point of view would be like with LSP, you don't actually have an actual symbolic model of the code.”
02 / belief
“At what point do we think that, you know, GPDX or whatever, you know, a pure, a transformer based LM model will be like state of the art or outperform the best like chess playing algorithm today? Because I think that is one milestone on...”
03 / belief
“I think, several key innovations away from happening right now. And I don't think the pure like transformer based LLM orchestrator modeled agents that is kind of like dominant today is going to get us there.”
04 / belief
“Oh yeah, I would say so OpenCodeGraph is not a DSL. It's more of a protocol. It's basically like, hey, if you want to make your system, whether it's, you know, chat or logging or whatever accessible to an AI developer tool like Cody, here's kind of like the schema by which you can provide that context and offer hints.”
05 / belief
“BFG is probably not the public name we're going to go with. I think we might call it like Graph Context or something like that.”
06 / belief
“We also had Han-Wen Nienhuys, who created Zoekt, which is, I think, heavily inspired by the Trigram index that powered Google's original code search and that we also now use at Sourcegraph.”
07 / belief
“Like, we have a couple of efforts where, like, we think fine tuning some models on specific coding tasks will yield more kind of, like, reliable code generation of the sort where it's, like, reliable enough that we can fully automate it, at least, like, the one hop thing.”
08 / belief
“I think maybe the interesting question is like looking at the different design decisions comparing LSP basically with Kythe.”
09 / belief
“I think that that does differentiate us from a lot of the other tools on the market, because a lot of people are going after this, like, shnazzy, like, inline edit interaction, whereas I think where we've moved, and this is based on the user feedback that we've gotten, it's like that sort of thing, it demos well, but when you're actually coding day to day, you don't want to have, like, a long chat conversation inline with the code base.”
10 / belief
“I think there are a couple of other technologies or approaches that need to be refined first before we can get into these kind of, like, multi-stage, fully automated workflows.”
11 / belief
“I think Copilot uses some variant of Codex. They're kind of cagey about it. I don't think they've like officially announced what model they use.”
12 / belief
“I think basically like the value profit of DSL is that it makes it easier to work with a lower level language, but at the expense of introducing an abstraction layer.”
13 / belief
“Even like the single hop, like write a function that does this. Because I think like if you want to get to the point where you can actually be truly agentic or like multi-step automated, a necessary part of that is like the single step has to be robust and reliable.”