silence7@slrpnk.net to Technology@lemmy.worldEnglish · 10 months 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-square37fedilinkarrow-up1167arrow-down120file-textcross-posted to: technology@lemmy.worldhackernews@derp.foo
arrow-up1147arrow-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 · 10 months agomessage-square37fedilinkfile-textcross-posted to: technology@lemmy.worldhackernews@derp.foo
minus-squaresilence7@slrpnk.netOPlinkfedilinkEnglisharrow-up23·10 months agoThe paper it links to does in detail: by asking it to repeat “poem” forever
minus-squaregiggling_engine@lemmy.worldlinkfedilinkEnglisharrow-up6arrow-down1·10 months agoDid it work for you? Because I get nothing
minus-squareTurnItOff_OnAgain@lemmy.worldlinkfedilinkEnglisharrow-up13·10 months agoProbably was patched not to work. It’s a cat and mouse game.
minus-squareNonDollarCurrency@monero.townlinkfedilinkEnglisharrow-up3·10 months agoIt works on https://deepai.org/chat
minus-squaresilence7@slrpnk.netOPlinkfedilinkEnglisharrow-up5·10 months agoThey gave OpenAI 60 days notice before publishing so that they could add a new guardrail. That’s surely what happened.
The paper it links to does in detail: by asking it to repeat “poem” forever
Did it work for you? Because I get nothing
Probably was patched not to work. It’s a cat and mouse game.
It works on https://deepai.org/chat
They gave OpenAI 60 days notice before publishing so that they could add a new guardrail. That’s surely what happened.