Kwasi Ankomah

We've seen it work really well in terms of, especially the larger 128B variation, right?

Mixture of experts handling computer vision.

So again, that's a very good model if you've got a vision problem.

When we set up some of these architectures, we use Maverick for kind of like predicted maintenance and stuff like that.

It does a really, really good job.

But I think...

the one the one that i think people has captured people's imagination and they they're able to because they're kind of just comparing it to frontier right has been probably v3 right v3 or r1 big and because r1 it's kind of you know it's reasoning expertise but v3 is just it's just a very strong and consistent model and i think you know it works to the point where you know if you did a kind of a blind test you'd be you'd struggle to see the difference

in its output between, especially the new 3.1 that's just come out as well, and 05-28.

They're really pushing at the door of the frontier model saying, hey, we are pitching ourselves directly against you.

And so it's a hard one to answer because they are, you know, but those are the ones to me that stand out.

And I think, you know, from what we're seeing from our clients and what I'm seeing when building agents, those are the ones, those are the models that really, really do give kind of stellar, stellar performance.

Yeah.

What do you think?

Yeah, we're kind of focusing on the inference side of things.

There's so many amazing model...

model providers and we want to focus our energy on making them as efficient as possible and making sure they run as fast as possible.

But yeah, we'll stay kind of on the infrastructure and optimization side of things.

Yeah.

It's, it's, it's very, very super cost-intensive.

As you said, it needs, needs a phenomenal team.