Mm-hmm

... to do that kind of math, is, is what I'm, is what I'm thinking.

And I'm not even sure that it's something the models can do themselves.

Like, in the same way that, like, I don't know, the code that...

And, and I, I complain about this, right? I'm not always happy with the code the agents produce, even if it works.

I think, again, one of the, you know, consequences of being a neckbeard and, like, reviewing lots of code is I've gotten used to the fact-

Yeah.

And, like, be- and, like, that's just sort of the nature of the beast over time, and that always gives me a certain sense of optimism and, like, that the stuff will persist.

Yeah.

We'll see how long this lasts.

Like, we'll see how...

I mean, eventually everything dies, right? But I'm, I've got a pretty good...

Uh, things have, things I've written have, have stuck around for a while, like that kind of thing, which is, which is sort of cool.

I think about it a lot these days, especially with, you know, the advent of AI and LLMs and trying to figure out, like, what does work mean anymore? What does it mean to be a data person? What does it mean to be a software engineer, right? And I think, like, the through line of my career, for better or worse, is, like, the fundamental problem of data engineering, which is, given that you have some data transformation task to do, how much of it do you do offline, kind of upfront as preparation work, and how much of it do you do online, like, at the moment that you need the data on the fly, right? And for me, like, all of data modeling, all of building search indexes, [chuckles] all of like...

I mean, what is, what is software engineering, but not like, "Hey, take some data over here in this place and do something to it and write it out over here at this other place"? Like, that's kinda all we do over and over again, and I am more or less obsessed with that problem, and kind of the arc of my career is, like, a search for new and interesting spins or approaches or constraints or variations of this fundamental problem.

[laughs]

Yeah.

And I had been a buyer of data tools for... for many years at that point.

And I knew...

What's missing? I knew what was missing.

I was like, I knew very much.

And so my sort of like filter was very, you know, very good.

Sharp, right.

Or is that what people call it? Yeah, that's what people are calling engineering.

We're going to the main event.

We, we, I would, like, me and Adam and Ryan, sometime we would DJ it, essentially, and then we would just play-

Yeah.

Yeah.

We, we would play, like, rap and hip-hop because I was just like, "I hear distortion and drums."