Lee Duna@lemmy.nz to Technology@lemmy.worldEnglish · 8 hours agoHackers Simply Asked Meta AI to Give Them Access to High-Profile Instagram Accounts. It Workedwww.404media.coexternal-linkmessage-square63fedilinkarrow-up1477cross-posted to: cybersecurity@infosec.pub
arrow-up1477external-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 · 8 hours agomessage-square63fedilinkcross-posted to: cybersecurity@infosec.pub
minus-squaregdog05@lemmy.worldlinkfedilinkEnglisharrow-up30·5 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.