Stern to [email protected]English • 1 day ago“Model collapse” threatens to kill progress on generative AIsbigthink.comexternal-linkmessage-square126fedilinkarrow-up1379arrow-down128
arrow-up1351arrow-down1external-link“Model collapse” threatens to kill progress on generative AIsbigthink.comStern to [email protected]English • 1 day agomessage-square126fedilink
minus-square@[email protected]linkfedilinkEnglish13•19 hours agoFake 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
minus-squareSabatalinkfedilinkEnglish1•6 hours agoAt this point the synthetic data is good enough to intentionally be used for training LLMs.
minus-square@[email protected]linkfedilinkEnglish3•5 hours agoYeah, just filter out the bad generated images and feed the good ones again, until the model learns how to produce only good ones.
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
At this point the synthetic data is good enough to intentionally be used for training LLMs.
Yeah, just filter out the bad generated images and feed the good ones again, until the model learns how to produce only good ones.