Mohammad Norouzi
👤 SpeakerVoice Profile Active
This person's voice can be automatically recognized across podcast episodes using AI voice matching.
Appearances Over Time
Podcast Appearances
And that was one of our goals.
We still want to produce tasteful output, but that doesn't mean we have to force a complex output to you.
If you want a minimalist design, you should be able to get that.
Actually, our minimalist is too minimalist in my opinion.
I was saying we should ban the word minimalist from the output.
But you get what I mean.
It's like the model can do many different things.
And that's by design.
Yeah, let's do it.
For the new branding.
Yeah, let's do it.
That's very exciting.
That's a very good question.
So in general, the recipe for building more powerful models, in my opinion, is making the task as straightforward as possible for the diffusion model.
specify the exact details of the image.
And so now if you kind of make that extreme, then it becomes the pixels themselves.
So the Fusion model doesn't have to do anything.
Now the catch is,
what we would like to do is to get the language model to produce that intermediate representation.