Mohammad Norouzi

So...

Kudos to the best designers who understand how these models work and are trying to figure this part out.

There's still a lot of work to do.

In terms of the things we've seen from the model, again, design is something that's coming up a lot.

And I saw a tweet before coming here that somebody said, I have no design training.

And I got this design in two minutes.

And it actually looked really, really nice.

That was one example.

And then people are really interested, excited about the art possibilities because this model was trained with very unique style description as part of training.

We actually stripped that from the JSON prompt because

it became too much but the model has a lot of artistic possibilities and like many different styles are embedded into the model and if you've seen some of the frontier models actually that score very highly in the leaderboards they don't have a lot of

kind of design variation.

They always produce the same exact look.

And I believe that's because they did a lot of reinforcement learning training.

They actually have done very little reinforcement learning.

So this is a very raw model.

Now with that, the outcome is you need to be much more precise with your prompting, but you can get a lot of different styles from the model.

And people seem to be very excited about that aspect of the model, especially in the art community.

Yeah, so we try to be

enabling very different styles.