Coding in Collaboration with AI with Sourcegraph CTO Beyang Liu

**Sarah** (0:06)
Hi, listeners, and welcome to another episode of No Priors. This week, we're talking to Beyang Liu, the co-founder and CTO of Sourcegraph, which builds tools that helps developers innovate faster. Their most recent launch was an AI coding assistant called Cody.
We're excited to have Beyang on to talk about how AI changes software development. Welcome.

**Beyang Liu** (0:24)
Cool. Thanks, Sarah. It's great to be on. Thanks for having me.

**Sarah** (0:28)
You guys founded Sourcegraph all the way back in 2013, right? I feel like I met you and Quinn at GopherCon either that year or the year after. Do you remember?

**Beyang Liu** (0:37)
Yeah, I think that's right. We met at one of those after-conference events, and I remember you asked me a bunch of questions about developer productivity and code search and what we're doing back then.

**Sarah** (0:48)
Many listeners to the podcast are technical, but can you describe the core thesis of the company?

**Beyang Liu** (0:52)
Quinn and I are both developers by background. We felt that there was this gap between the promise of programming, being in flow and getting stuff done and creating something new that everyone experiences. It's probably the reason that many of us got into programming in the first place, the joy of creation. Then you compare that with the day-to-day of most professional software engineers, which is a lot of toil and a lot of drudgery. When we drilled into that, why is that? I think we both realized that we're spending a lot of our time in the process of reading and understanding the existing code rather than building new features, because all that is a prerequisite for being able to build quickly and efficiently.
That was a pain point that we saw again and again both with the people that we collaborated with inside the company we were working at at the time, Palantir, as well as a lot of the enterprise customers that Palantir was working with. We were drop shipping into large banks and Fortune 500 companies and building software embedded with their software teams and if anything, the pain points they had around understanding legacy code and figuring out the context of the code base so they could work effectively was 10x, 100x of the challenges that we were experiencing.
It was partially scratching our own itch and partially like, hey, the pain we feel is reflected across all these different industries trying to build software.

**Sarah** (2:14)
Yeah, we're going to come back to context and how important it is for using this generation of AI, but I want to go actually back to some roots you have in thinking about AI and your interning at the Stanford AI Research Lab way back when.
That wasn't the starting point for Sourcegraph. It was more like, oh, we need super grep, right? We just need a version of search that works in real environments and is useful for getting to flow. When in the story of Sourcegraph did you start thinking about how advancements in AI could change the product?

**Beyang Liu** (2:47)
My first love in terms of computer science was actually AI and machine learning. That's what I concentrated in when I was a student at Stanford. I worked in Stanford AI Lab with Daphne Koller, she's my advisor, mostly doing computer vision stuff in those days. It was very different in those days. We're now living through the neural net revolution. We're well into it. It's just like neural nets everywhere.
In those days, it's still the dark ages of neural nets, where it was after the first initial successes they had in the late 80s and 90s doing OCR with them.
But then after that, the use cases petered out. By the time that I was doing it, the conventional wisdom, the thing that they told us in Machine Learning 101 was neural nets were this thing that we tried a decade or so ago, but it didn't really pan out. These days, we're mostly focused on graphical models and statistical learning techniques, really trying to be explicit about modeling the probability distribution of what we're trying to represent.

**Sarah** (3:48)
We actually had Daphne and one of her other former students, Lucas B. Wald from Now Weights and Biases, on the podcast as well. And both of them were also lamenting the dark ages when neural nets were this weird niche thing. We're going to work on graphical models instead.
But it's very cool to see so many people who have an interest and technical passion in this emerge the other end and be like, aha, now is the time. At what point were you like, okay, I'm going to look at this and we're going to try to work on it at Sourcegraph?