silence7@slrpnk.net to Technology@lemmy.worldEnglish · 2 years 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-square39fedilinkarrow-up1184arrow-down119file-textcross-posted to: technology@lemmy.world
arrow-up1165arrow-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 · 2 years agomessage-square39fedilinkfile-textcross-posted to: technology@lemmy.world
minus-squarebloopernova@programming.devlinkfedilinkEnglisharrow-up16arrow-down2·2 years agoWorrying that OpenAI wasn’t willing or able to fix this vulnerability within 60 days.
minus-square∟⊔⊤∦∣≶@lemmy.nzlinkfedilinkEnglisharrow-up10·2 years agoI think this might be intrinsic. Like, there isn’t a way to fix this.
minus-squareStelus42@lemmy.calinkfedilinkEnglisharrow-up3·2 years agoWell something certainly seems to have been done
minus-squareinspxtr@lemmy.worldlinkfedilinkEnglisharrow-up3·2 years agoSomething like this, unless they know the root cause (I didn’t read the paper so not sure if they do), or something close to it, may still be exploitable.
Worrying that OpenAI wasn’t willing or able to fix this vulnerability within 60 days.
I think this might be intrinsic. Like, there isn’t a way to fix this.
Well something certainly seems to have been done
Something like this, unless they know the root cause (I didn’t read the paper so not sure if they do), or something close to it, may still be exploitable.