Paul Dix

And it spanned across, you know, maybe like over a hundred thousand lines of code.

But when you start up Claude or Codex or whatever,

they won't read an entire file if it's more than whatever, like 2,500 lines.

No, 2,500.

Yeah.

I mean, definitely like, so any code file that's like 20,000 lines of code, it will not read.

So basically like it'll sample little pieces and,

And I think what that leads to, again, this is just my theory of like, I think like the result isn't as good because you're only get a sampling of the thing and basically it doesn't have the context it needs to make good choices.

So I still think you need a lot more, you know, professional developer involvement

When it comes to architecturally, how do you organize the code?

How do you kind of like break down the problem?

Like if you have this big problem that you're trying to solve, how do you break it down into smaller chunks so that you don't have to keep the entire thing in your head at once?

Which is important for developers, but it's also important for agents too, right?

So part of this is code files that just, you don't let code files get that big, right?

You break them up ahead of time.

You make clear what the invariance of a system are and what the expectations are.

And you make it so that the agents can read those out quickly and easily to get the context for anything they're working on within a system.

But for our engineering team this year, my expectation, everybody's using these tools.

And my expectation is we're going to spend a lot of time building

QA suites and things like that, that essentially like...