readbeanicecream@lemm.ee to technology@lemm.eeEnglish · 9 months agoResearchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious querieswww.tomshardware.comexternal-linkmessage-square0fedilinkarrow-up111arrow-down10cross-posted to: technology@lemmy.world
arrow-up111arrow-down1external-linkResearchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious querieswww.tomshardware.comreadbeanicecream@lemm.ee to technology@lemm.eeEnglish · 9 months agomessage-square0fedilinkcross-posted to: technology@lemmy.world