Ahmed El-Kishky

The model has to be creative because it isn't like the traditional, this is correct, this is incorrect.

Model, you have to, you know, submit solutions and then looking at like how well it did, it would have to then one up itself.

So it was really in a competition against itself to sort of get better and better solutions.

And we'd never tried these out before.

And so we wanted to sort of see how we did.

One example of these competitions or these problems are like games.

Sometimes some games, there's no like best game or anything or best program, but you can sort of just get better and better at it.

Yeah, yeah, I'll talk a little bit about ICPC.

It's honestly just a team sport here.

I don't even want to say it's just a handful of people.

It's the byproduct of pre-training our models and then doing RL on them in general to make them really great reasoners, really great tool use.

And then afterwards, there's so many people that contributed different ML aspects to the models.

The experimental reasoning model we used was a byproduct of the IMO efforts by Alex Wei, Cheryl, Noam.

So there's so many people sort of playing a part here.

But the core people that actually went to Azerbaijan, it's almost like a volunteer experience.

We're just like, hey, who wants to try this out?

And Mustafa was one of them.

We had Robin and we had Andrew and Boris was helping out from London.

So they formed almost like the core team of people that were, you know, driving this.

A lot of it was sort of making sure the models were ready to go because there's no room for error here.