1. Generate UI with gpt-image-2
2. Generate a normal map from the image
3. Dynamic lighting for UI components - raised elements actually cast shadows and get lit naturally.
@GregFeingold This is a really great addition!
Hope to see a standardized interoperability for importing chats (or just memories) between Claude, ChatGPT, Gemini in the future.
You can capture reality with remarkable fidelity - here’s a 1:1 3d gaussian splat perfectly aligned with reality.
Once Meta layers in a scalable version of their codec avatar tech - this stuff is about to get trippy. Literally transcending time & space.
i'm hiring at apple!
ship high-impact AI experiences with us.
- location: apple park
- pay: base up to $272k
- stack: python/swift/java and react
DM me or share (if you know someone passionate)!