Grant Harvey

And then I was thinking, that would sound kind of wild if, like, all of a sudden it comes out and it's like, and then you have the, like, you hear the sound wave generate.

But then also I was thinking, I'd love your take on that, if it's even possible.

But then also I was thinking, well, it makes sense to try and, you know, perhaps match it with a...

speech to text model, because it makes sense to that's where you need the most real time interactions, right?

As if you're having a voice to voice conversation.

So that makes obvious sense to me.

I'm curious how that's going.

That's blowing my mind.

How would a computer use, this might be giving secret sauce away, but how would a computer use diffusion LLM work?

Like, is it generating the whole screen space?

Like what, how does that work?

But how is it, I guess what I was wondering is how is it seeing it?

How is it like see the, and that's, I guess it's maybe more so on the vision model.

That's really neat.

Just to clarify, is that a vision action model or is that a different type of model?

Okay.

Yeah.

Well, OpenAI had this paper not too long ago, right, that was saying that basically like hallucinations are a training problem, or at least that was their thesis, that, you know, the models are effectively being rewarded for guessing as opposed to saying when they don't know.

Do you buy into that?

Do you subscribe to that idea?