I don’t know if thinking that training data isn’t going to be more and more poisoned by unsupervised training data from this point on counts as “in practice”
The inbreeding could also affect larger decisions in sneaky ways, like how it wants to compose the image. It would be bad if the generator started to exaggerate and repeat some weird ai tropes.
Yeah, in practice feeding AI its own outputs is totally fine as long as it’s only the outputs that are approved by users.
I don’t know if thinking that training data isn’t going to be more and more poisoned by unsupervised training data from this point on counts as “in practice”
I would expect some kind of small artifacting getting reinforced in the process, if the approved output images aren’t perfect.
Only up to the point where humans notice it. It’ll make AI images easier to detect, but still pretty for humans. Probably a win-win.
Didn’t think of that, good point.
The inbreeding could also affect larger decisions in sneaky ways, like how it wants to compose the image. It would be bad if the generator started to exaggerate and repeat some weird ai tropes.