News for hackers. Stuff that matters.
Re:Invasive Diffusion: one unwilling illustrator found her t... by peoplefromibiza on Tuesday November 01, 2022 @05:43PM (#33427957)
> there aren't enough bits

you can create compressed copy of a file containing 100TB of the letter "A" in much less than 4GB

there could be enough bits in there to reproduce some of the inputs.

Re:Invasive Diffusion: one unwilling illustrator found her t... by CuriouslyC on Tuesday November 01, 2022 @05:52PM (#33428082)
What this analogy is saying is that if an image is generic and derivative enough (or massively overrepresented in the training data) it may be possible to reconstruct a very close approximation from the model. If the training data is unbiased, I question the validity of copyright claims on an image that is sufficiently derivative that it can be reproduced in this manner.