Yoko Li
π€ SpeakerVoice Profile Active
This person's voice can be automatically recognized across podcast episodes using AI voice matching.
Appearances Over Time
Podcast Appearances
Now, so much of that may become like an API request, like the agent makes.
How do you see that?
What would the API entail compared to how humans use it?
I guess for the API business, so much of a design is iteration.
It's a long tail of a design.
It's no longer just you prompt something, you get an image and call it a day, right?
It's so much of a get an image, use the edit model to edit it, see if it works well.
If it doesn't, get another image with the JSON flop, which is easier for control.
What are the net new use cases you have seen after launching a model of how people do, like, compose different API calls on the Ideogram bot?
We know what's the first ideal brand model.
We're going to your post train.
It will be an A16Z marketing brand style art deco.
A16Z art deco.
Yeah, so I guess the question also becomes like, I kind of asked you the representation question before, which is, here's a JSON representation.
As an artist, obviously, if you abstract it out, you know, far enough, all the lines are pixels.
So you could say that the composability is on the pixel level, which is actually different from the diffusion representation.
It's like denoising and, you know, they operate in a different space.
Where does this lead to if you travel down the JSON path granular enough?
Does it lead to pixels?