Lee Duna@lemmy.nz to Technology@lemmy.worldEnglish · 12 hours agoHackers Simply Asked Meta AI to Give Them Access to High-Profile Instagram Accounts. It Workedwww.404media.coexternal-linkmessage-square77linkfedilinkarrow-up1622arrow-down11
arrow-up1621arrow-down1external-linkHackers Simply Asked Meta AI to Give Them Access to High-Profile Instagram Accounts. It Workedwww.404media.coLee Duna@lemmy.nz to Technology@lemmy.worldEnglish · 12 hours agomessage-square77linkfedilink
minus-squaregdog05@lemmy.worldlinkfedilinkEnglisharrow-up36·9 hours agoI honestly don’t think you can create guard rails against prompt engineering in a working LLM. At some point, they’re going to fail or the LLM isn’t functioning. The only solution is to make sure they can’t read data you don’t want shared.
I honestly don’t think you can create guard rails against prompt engineering in a working LLM. At some point, they’re going to fail or the LLM isn’t functioning. The only solution is to make sure they can’t read data you don’t want shared.