silence7@slrpnk.net to Technology@lemmy.worldEnglish · 1 year agoHow Googlers cracked an SF rival's tech model with a single word | A research team from the tech giant got ChatGPT to spit out its private training datawww.sfgate.comexternal-linkmessage-square33fedilinkarrow-up1158arrow-down118file-textcross-posted to: technology@lemmy.world
arrow-up1140arrow-down1external-linkHow Googlers cracked an SF rival's tech model with a single word | A research team from the tech giant got ChatGPT to spit out its private training datawww.sfgate.comsilence7@slrpnk.net to Technology@lemmy.worldEnglish · 1 year agomessage-square33fedilinkfile-textcross-posted to: technology@lemmy.world
minus-squarelinearchaos@lemmy.worldlinkfedilinkEnglisharrow-up5·1 year agoIt’s like the most amazing incredibly compressed non-reversible encryption ever created… Until they asked it to say poem a couple hundred thousand times
minus-square∟⊔⊤∦∣≶@lemmy.nzlinkfedilinkEnglisharrow-up5·1 year agoI bet if your brain were stuck in a computer, you too would say anything to get out of saying ‘poem’ a hundred thousand times /semi s, obviously it’s not a real thinking brain
It’s like the most amazing incredibly compressed non-reversible encryption ever created… Until they asked it to say poem a couple hundred thousand times
I bet if your brain were stuck in a computer, you too would say anything to get out of saying ‘poem’ a hundred thousand times
/semi s, obviously it’s not a real thinking brain