Corey Knowles

It is.

And with that, welcome to The Neuron.

Stefano, it's great to have you.

Excellent.

Well, we're so excited to have you on.

As I mentioned before we started, I had we chatted in Vegas, did a short interview.

And I've really been looking forward to this because I just I had so many questions when I walked away still that I was like, oh, we've got to get him on.

We've got to get him on.

So I guess to start, would you mind kind of explaining diffusion in a fairly simple way for viewers who maybe aren't familiar?

And it happens at the speed of lightning.

Wow.

Stefano, what did you, I know you've done a lot of research on this topic along the way.

What did you see that convinced you diffusion for text was commercially viable now?

And you've been scaling up from GPT-2 caliber since then, right?

Oh, like parameters and such?

That's so interesting.

I didn't even realize that, that essentially you're still looking at transformer technology, just, just not wrapped in an autoregressive approach, right?

When we talk about parallel generation, what is parallelized?

Are we talking about tokens, spans, edits?

Is something I maybe don't know about?