Noam Shazeer

And, you know, that's part of kind of one of the things that PathWave was designed to support is

you have these components and the components can be in variable cost.

And you kind of can say, for this particular example, I want to go through this subset of the model.

And for this example, I want to go through this subset of the model and have the system kind of orchestrate that.

But it also means, I think, you don't necessarily need to grow your entire model footprint to be the size of a data center.

You might want it to be a bit below that.

and then have, you know, potentially many replicated copies of one particular expert that is being used a lot so that you get better load balancing.

Right, interesting.

So, like, this one's being used a lot because we get a lot of math questions, and this one on, you know, maybe it's an expert on Tahitian dance, and it is called on really rarely.

That one maybe you even page out to DRAM rather than putting it in HBM.

But you want the system to kind of figure all this stuff out based on load characteristics.

Yeah.

I mean, you're starting to see some of this by having a lot of uses of Gemini models across Google that are not necessarily, you know, fine-tuned.

They're just sort of

you know, given instructions for this particular use case and this feature in this product setting.

So I definitely see a lot more sharing of what the underlying models are capable of across more and more services.

You know, I do think that's a pretty interesting direction to go for sure.

Yeah, and I think you might see that might be a big base model, and then you might want customized versions of that model with different modules that are added onto it for different settings that maybe have access restrictions.

Like maybe we have an internal one for Google use for Google employees that we've trained some modules on internal data, and we don't allow anyone else to use those modules.

we can make use of it and maybe other companies you add on other modules that are useful for that company setting and serve it in our cloud APIs.