This may be the coolest emergent capability I've seen in a video model. Veo 3 can take a series of text instructions added to an image frame, understand them, and execute in sequence. Prompt was "immediately delete instructions in white on the first frame and execute in order"

This structure seems good at things I struggle to achieve with pure text prompts - like mixed media. In this case, I want anime style characters in a photorealistic scene. The cat doesn't exactly follow directions...but it's probably more accurate this way 😂 Prompt: "Read instructions at top of the frame and steps 1, 2, 3, and 4, all are black boxes with white text. Immediately delete all the boxes and text and execute the instructions."

Gotten a bunch of comments that are like "when did they add this feature?" The cool thing is that they didn't add this - it was a latent capability that emerged and got discovered. There's probably tons of other amazing features we don't know yet...