Cognition’s Scott Wu on how Devin, the AI software engineer, will work for you

**Sarah Guo** (0:05)
Hi, listeners, and welcome to No Priors. Today, we are talking to a very good human software engineer and the co-founder and CEO of Cognition, Scott Wu. The team at Cognition calls themselves an AI lab focused on reasoning. And recently, they released a demo of Devin, an AI software engineer that can increasingly handle entire tasks end to end, with leading results on Sweetbench, a software engineering benchmark of real-world GitHub issues.
The demo broke the internet, at least among tech Twitter. And so we're really excited to have Scott. Welcome, Scott.

**Scott Wu** (0:35)
Hey, great to be here. Thanks for having me.

**Sarah Guo** (0:37)
So you have been coding and then coding competitively since you were a kid. What first got you interested?

**Scott Wu** (0:46)
I always really, really liked math growing up actually. My older brother, Neil, was the first to get me into programming. So I think I learned how to program when I was around nine years old. I just fell in love with it. I think the ability to take ideas and then make them into reality was always really exciting for me. I did a lot of math and programming competitions throughout school.
By the time I finished high school, I was pretty set on going into tech.

**Sarah Guo** (1:12)
Can you explain for some set of our listeners that are not familiar, like what IOI is?

**Scott Wu** (1:19)
Yeah, sure. So IOI is the International Olympiad of Informatics. So it's the Olympiad of code basically.
It works just like the other Olympics. Every country sets in their own team of their best coders, and it's a competitive programming competition.
There's gold medals, silver medals, bronze medals, and so on. The whole idea is it's very algorithmic problem-solving. So you're given tasks to solve and you have to figure out the optimal algorithms for those and then also implement those into code.

**Sarah Guo** (1:53)
It's like a interesting topic for somebody who was world-class at IOI. What is practice like for getting better at competitive programming?

**Scott Wu** (2:05)
Programming and math competitions used to be my entire life when I was growing up.
What you think about the shower, it's what you're spending all your time on. Every problem in life that I run into, I frame as an algorithm's problem basically. Like a lot of other disciplines, it's just putting a lot of effort into it and be willing to think really analytically and be very brutal about your own shortcomings and focus on the things that you're not doing well and just continue to push and improve.

**Sarah Guo** (2:39)
Is it like a known space of domains and algorithms one can learn, or is it really like learning to solve problems algorithmically really well, and it could be completely new problems or domains in every competition?

**Scott Wu** (2:54)
Yeah, there's definitely, there are standard algorithms that exist. So like shortest path or something or binary search trees or things like that. And so it helps a lot to learn the fundamentals. But the whole idea is that every problem in a contest is totally unique. It's a new problem that's never appeared before.
And the beauty of the contest itself is in the creative problem-solving that you're doing to figure out the right algorithm, right? And so while the fundamentals are very helpful, a lot of it is figuring out how to use each of these pieces and reduce the problem to a shortest path problem or how you modify certain algorithms to make them work for different use cases.

**Elad Gil** (3:35)
I feel like there's a whole generation of people now who are basically people who grew up with the Internet being their hometown in some sense. Where a lot of their early community or people they interact with sort of come from that world. And I feel like that's a lot of people in the AI world today.
Was that true for the IY community as well? Was it largely like online interactions and trading tips with strangers who became friends and all that kind of stuff? And then if so, how has that impacted your career or your life or working with others over time?

**Scott Wu** (4:03)
Yeah, definitely. I mean, I grew up in Baton Rouge, Louisiana. And so there were not a lot of other people who had the same kind of interest in math and programming that I did. And so a lot of these competitions were the first time that I got to meet others who had a lot of these same interests. And the competitions are once a year, and maybe there's training camps or things like that that are a couple of times a year. But for the large majority of the year, we'd be talking online. And we had all of our own communities where we'd talk about competition problems, but also kind of, yeah, we became very close friends too.