The Exchanges

Q What do you think are some of the tips for anyone that wants to build a coding agent since you've done it a lot? What are, what are some now lessons that you learned that you want to share?

A I mean, I think the number one thing, uh, is managing context. Well, basically we kind of had like a checkpoint. For, uh, I think it was O three, like one of the reasoning models. And then we did a bunch of fine tuning on it, um, and reinforcement learning where it's like, oh, you're given a bunch of questions to like solve these coding problems or like fixed tests or whatever, implement a feature. Um, and then the model was RL to respond to those. And so I think most people are not going to be doing that. Right. But the things that you can do are figure out like, Hey, what context should I be supplying to this agent to get the best possible result? And so for cloud code, if you watch it working, it's like, oh, I'm going to like spawn a bunch of these explore sub agents. They will like search for different patterns in the file system. They will come back. Uh, they will have this context. They'll summarize it for me. And then I'll have someplace to go. It's interesting watching like different agents structure this context. Uh, like I think cursor takes an approach where they actually do semantic search, where they embed everything and figure out like, Hey, what query is closest to this? If you look at a codex or a cloud code, uh, they actually just use like grep. Uh, and I think that works because well, yeah, it works very well because code is very context dense. Um, like if you…

AI assessment note: “I think the number one thing, uh, is managing context.”

Q Yeah, what do you do to be so productive with it?

A One is if you're able to use, uh, just generally far less code and plumbing, Um, so a lot of what I do is like deploy stacks on like Vercel or Next.js or like Cloudflare workers, where there's kind of like already a bunch of boilerplate, like taking care of for you. And then you don't really have to think that much about like, Hey, I need to stand up like all these different services and deal with like service discovery and like registering on like some sort of central endpoint or like all these databases. It's like, Oh, like everything is pretty roughly defined in this, like one or 200 lines of code. I, Tend to operate more towards microservices for that as well, or like individual packages that are fairly well structured. I think it's also worth knowing like what the LLM superpowers are. Like in general, coding agents are, I think Andrej Kharapathy just tweeted about this. They're like super persistent, so they will keep going no matter what. They end up, uh, typically just making more of whatever's there. So if you're trying to direct them to do something, it's worth like I mean, I can pick on OpenAI slightly in this example. OpenAI has, like, a giant monorepo. It's been there for a few years now and has, like, I don't know, thousands of engineers who are committing. Some of those engineers are like super senior meta folks who came in and are like, know exactly how to write …

AI assessment note: “One is if you're able to use, uh, just generally far less code and plumbing”

Q Do you have thoughts, just because you know the, the agent's so wild, like, what, what types of engineers are going to benefit more than others, um, from these tools becoming popular?

A In general, I think that kind of the more senior, senior you are, the more you benefit, um, because the agents are so good at taking some sort of idea and then putting it into action. If you're able to prompt that in a few words, it's kind of like, oh, now suddenly I had this like idea. I find this so often open AI, like strolling through the code base. It's like, oh, like, here's the thing that I wish were different. Here's the thing that I wish were different. Here's the thing that I wish were different. Like just being able to kick those off and then have them come back, I think is Super empowering and multiplies your impact. I think also being able to detect like which sorts of changes are good or bad architecturally is very important or like have a sense for where you might want to flag something to an agent. I think engineers who are more organized, like manager ish, uh, and there's probably just a missing product to be built here. Uh, maybe something like conductor, uh, where it's like spread across all of your sessions and kind of reminding you like, Hey, you were working on this thing. It's done. It needs your input here. Oh, you should switch your attention over to this other thing. I think that is.

AI assessment note: “the more senior, senior you are, the more you benefit”

Q So if you were going back to your, like, college days and studying CS again fresh and you, like, were picking your own, like, syllabus or curriculum, like, what would you, what would you study?

A Personally, I think still understanding systems, uh, is very important, um, and just having some conception of, like, how, like, Git works, you know, or, like, HTTP, or databases, like, queues, like, all of these different systems. I think that those fundamentals are still quite important. The other thing that I'd probably do is just have a semester where like each week you're just building something and you really try and push the models as far as they can go. There's a sense that you have whenever you're doing something that you could always just like go up the layer and ask the model to do it and like go up a layer and ask the model to do it. You know, it's like, oh, I have like a implement command where it like implements the next phase of the plan, but then I could have like an implement all command and it like goes stage by stage and creates a new sub agent. And then I could have like a check your work kind of thing and like. And I think knowing where the models can and can't accomplish that is such a moving target that it's worthwhile just to, like, tinker a lot.

AI assessment note: “Personally, I think still understanding systems, uh, is very important, um, and just having”