shish_mish@lemmy.world to Technology@lemmy.worldEnglish · 9 months agoResearchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious querieswww.tomshardware.comexternal-linkmessage-square24fedilinkarrow-up1299arrow-down14
arrow-up1295arrow-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 · 9 months agomessage-square24fedilink
minus-squarespujb@lemmy.cafelinkfedilinkEnglisharrow-up3arrow-down3·9 months agoyes i am aware? are they being used by openai?
yes i am aware? are they being used by openai?