Kbin_space_program@kbin.social 9 months ago
The issue is also present in DallE and bing image generation. Hypothesis is the sheer amount of porn being generated is affecting the models.
When I tried to create a joke profile for Tinder with some friends, I tried "woman eating fried chicken". Blocked result. "Man eating fried chicken" works.
Tried "Man T posing on beach" clothed. Woman T posing on beach, blocked.
Woman t posing at sunset on beach, returned nearly silhouetted nude image. Same thing for guy, clothed.
Went back to the first one, had to specify that the woman was wearing clothes to make it return the image. Sometimes specifying specific articles.
Deceptichum@kbin.social 9 months ago
Your hypotheses makes no sense?
People generating porn would make no change to its training data set.
Kbin_space_program@kbin.social 9 months ago
You wouldn't feed the images people generate and save back into the system to improve it?
DoYouNot@lemmy.world 9 months ago
This actually doesn’t work to improve the model, generally. It’s not new information for it.
Deceptichum@kbin.social 9 months ago
Not after the initial training, no.
That would make it less effective, because instead of being trained on known real things it’s being further reinforced on its own hallucinations.