What racing reveals about working with AI - Episode 22

Has there been some point where you said, "Oh, wow, I can clearly see the difference"?

You know, starting out, I, there, there was a lot that, that I knew I had to learn-

Mm

... about what was happening, you know, behind the scenes and with the teams.

Being on the inside of it n- now, I guess, like, yeah, I, I have always held on to the notion that anyone has the ability now to, to organize things in a way to where you can kind of get what you need faster, right?

Mm-hmm.

And I think that that, for me, is probably still the thing that still rings true.

It's, it's always gonna be about who can organize the best.

It's always gonna be about who is, you know, who, who is knowledgeable on a certain track or certain corners-

Mm-hmm

... or, um, you know, understanding, you know, a driver the best way or understanding the limitations that you have on your team.

Uh, a- and for me, it was always about whoever can put that together the best and the quickest is probably going to see a huge uptick in their results over a season.

I think a big thing that I wanna know from you is, you know, what are, what are some of the things that you've found where you're able to deliver exactly what you're being asked to deliver, and like, and what are...

What, what is, I guess, like, the most smallest little detailed thing that you've been able to deliver to the team that may not seem like anything to anyone else, but it makes all the difference to everything that you're doing operationally on the track?

One of the most impactful things that we've delivered to the team is, frankly, is education.

Um, it's education on, uh, a little bit about how our models work.

I think it helps to pull back the veil and show that these are just machines under the hood, and it's not magic.

Um, and, uh, these guys are engineers, and they understand that, and once you understand how the machine is built, it's easier to conceptualize how to work with them better.

So that's ta- taken the form of, um, you know, prompt engineering is something that, uh, has, uh, Andrew, you are the original expert prompt engineer.

[laughs] But yeah, just showing them, for example, that, uh, it's all about the input.

It's, um, if you give it the right input, you'll get the output you're looking for.

And, um, so there's some onus on you as the user to figure out what that right input is.

And, um, you know, frankly, what we do with Chip Ganassi, uh, we do a lot of prep work ahead of- Ahead of the race day.

I mean, these guys are just, they're so good at what they do.

They know exactly what they need once race day comes.