Stern to Technology@lemmy.worldEnglish • 2 days ago“Model collapse” threatens to kill progress on generative AIsbigthink.comexternal-linkmessage-square121fedilinkarrow-up1361arrow-down128
arrow-up1333arrow-down1external-link“Model collapse” threatens to kill progress on generative AIsbigthink.comStern to Technology@lemmy.worldEnglish • 2 days agomessage-square121fedilink
minus-square@levzzz@lemmy.worldlinkfedilinkEnglish13•23 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•10 hours agoAt this point the synthetic data is good enough to intentionally be used for training LLMs.
minus-square@Honytawk@lemmy.ziplinkfedilinkEnglish2•10 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.