Inside Steve Yegge's Software Factory: Lessons from Running 50 Agents

Yeah, super interesting stuff.

I mean, the thing with the oscillating that you mentioned before, right? I often also think it's like there's so many dynamics here, right? It's the agents between them, the humans between the humans, humans and agents, then human with agents with human without agents.

There's also like a strong dynamic happening around there.

I don't know.

I mean, I often, often it feels like, like there's so much stuff going on that you are like, this oscillating also comes from the social and human and overwhelming side of all of this.

I think then you just at a certain point, you kind of need a break, basically.

Yeah, and again, if you need that in your factory, and I am adding it, you need something that I'm calling a pace gate, which is basically a mechanical fence of some sort that keeps them from going too fast.

Whether they get an email budget or a Slack budget, a Discord budget, whatever it is, they're allowed to talk on those channels, but they have to be within certain budgets.

And as long as they have that mechanical restriction, then they tend to do a little bit better, right? But what you can't do is say, just have common sense, because they will not, they absolutely will not,

right? Oh, but I really like the idea.

I haven't thought about that yet, that you say there's a budget for messaging, like amount of messages or what you also said before, like system resources and also all of that kind of, so that you, then they can really measure, okay, I sent three messages already and now I'm not allowed to send any more.

I mean, we are really going to get into an issue when the tokens per second get up, right? So currently we are in a very slow phase still because all of that is like only 50 or 60ish tokens per second, right? And fast mode, okay, it's a little faster, but yeah, it's a good idea in the end to limit it with these hard gap rates.

It's a good idea.

Yeah.

I mean, you know, and So there's that, right? There's the whole putting a governor and semaphores on top of all resource usage where you consider even things like attention to be resource.

Like, yeah, even something as simple as attention, if left unchecked, can produce huge hidden side effects that you discover once they're problematic, right? Like, just case in point, just to cite one example, last night I asked my factory when it was going to be done repairing itself.

And it went, oh, let me run a script.

Let me do some checks.

Let me run some numbers.

They're very good at measuring things, right? I'm going to get a complete picture before I guess anything for you.

All right, okay, I got your answer.

The answer is never.

And I was like, excuse me, sorry, because I was expecting an answer more like tomorrow or today, like so that we're done and we can move on.

And it was like, well, no, I'm just saying that's what the numbers are showing us.

We are never going to be finished because what was happening was my agents, and this is a message to, I mean, like everyone should hear this loud and clear, all right? I gave them beads, and beads is a scratch pad for them to basically record, you know, their whatever, their thoughts, anything they find, bugs in passing, so that they no longer drop work, okay? They retain it.