Stern@lemmy.world to Technology@lemmy.worldEnglish · 2 months ago“Model collapse” threatens to kill progress on generative AIsbigthink.comexternal-linkmessage-square150fedilinkarrow-up1458arrow-down128
arrow-up1430arrow-down1external-link“Model collapse” threatens to kill progress on generative AIsbigthink.comStern@lemmy.world to Technology@lemmy.worldEnglish · 2 months agomessage-square150fedilink
minus-squarelevzzz@lemmy.worldlinkfedilinkEnglisharrow-up15arrow-down3·2 months 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-squareSabata@ani.sociallinkfedilinkEnglisharrow-up1·2 months agoAt this point the synthetic data is good enough to intentionally be used for training LLMs.
minus-squareHonytawk@lemmy.ziplinkfedilinkEnglisharrow-up3·2 months 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.