Comment on “Model collapse” threatens to kill progress on generative AIs
levzzz@lemmy.world 2 months ago
Fake news, just like that one time Nightshade “killed” stable diffusion (literally had no effect) Flux came out not long ago and it’s better than ever
Sabata11792@ani.social 2 months ago
At this point the synthetic data is good enough to intentionally be used for training LLMs.
Honytawk@lemmy.zip 2 months ago
Yeah, just filter out the bad generated images and feed the good ones again, until the model learns how to produce only good ones.