Andy Halliday

Llama does 21.

Gemma does 14.

Quinn does 43 and

And LFM 2.5 does 44.

So these two models, QUIN 3 1.7B instruct and the LFM 2.5 1.2 billion instruct are very,

far and away above the accomplishments on this massive multitask language understanding benchmark than are the Gemma 3 model at 1 billion and the Lama 3.2, 1 billion models.

So, you know, this is part of the progress that's being made toward the day when this is going to be your primary interface device and it's going to be running its own local model.

It's me, Malti.

Okay, I think we have to wrap up because I got to go.

And my attention and my list of news items dwindled to nothing.

So Sakana is the ninja of AI.

They're not doing large scale model training.

What they're doing is finding the clever ways to slice and dice with novelty and innovation.

And this is why Google's interested in them, because scaling is kind of reaching a limit.

of what you can accomplish.

And the founder of Sakana, the guy named Leon Jones was one of the authors of the attention is all you need paper, which goes back.

So he's from, he's like one of the O G a I thought leaders.

And he's built Sakana over in Japan and,

And so there were eight authors of Attention is All You Need.

He's one of them.