shish_mish@lemmy.world to Technology@lemmy.worldEnglish · 10 months agoResearchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious querieswww.tomshardware.comexternal-linkmessage-square24fedilinkarrow-up1298arrow-down14cross-posted to: [email protected]
arrow-up1294arrow-down1external-linkResearchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious querieswww.tomshardware.comshish_mish@lemmy.world to Technology@lemmy.worldEnglish · 10 months agomessage-square24fedilinkcross-posted to: [email protected]
minus-squarespujb@lemmy.cafelinkfedilinkEnglisharrow-up1·10 months agothe fact that you explained the problem doesn’t make it not a problem
the fact that you explained the problem doesn’t make it not a problem