You could probably make some semi-realistic drawings and feed those in, and then re-train the model with those same images over and over until the model is biased to use the child-like properties of the drawings but the realism of the adult pictures. You could also feed the most CP-looking images from a partially trained model as the training data of another model, which over time would make the outputs approach the desired result.
Comment on 25 arrested in global hit against AI-generated child sexual abuse material
DoPeopleLookHere@sh.itjust.works 1 day agoIt was able to produce that because enough images of both feet and Donald Trump exist.
How would it know what young genitals look like?
JuxtaposedJaguar@lemmy.ml 1 day ago
DoPeopleLookHere@sh.itjust.works 1 day ago
But to know if it’s accurate, someone has to view and compare…
JuxtaposedJaguar@lemmy.ml 1 day ago
It doesn’t matter if it’s accurate or not as long as pedos can get off to it, so just keep going until they can. According to our definition of what a pedophile is, though, it would likely be accurate.
DoPeopleLookHere@sh.itjust.works 1 day ago
But if it’s not accurate, will pedos jerk off to it?
JuxtaposedJaguar@lemmy.ml 1 day ago
If you train a model on 1,000,000 images of dogs and 1,000,000 images of cats, your output isn’t going to be a 50/50 split of purely dogs and purely cats, it’s going to be (on average) somewhere between a cat and a dog. At no point did you have to feed in pictures of dog-cat hybrids to end up with that model.
DoPeopleLookHere@sh.itjust.works 1 day ago
Yes but you start with the basics of a cat and a dog. So you start with adult genitals and…
JuxtaposedJaguar@lemmy.ml 1 day ago
Non-pornographic pictures of children and/or human-made pornographic drawings of children.
DoPeopleLookHere@sh.itjust.works 1 day ago
Okay, and those drawings are my problem.
icenews.is/…/unsavoury-cartoon-ruling-sparks-deba…
It’s not clear cut that those are okay.