shish_mish@lemmy.world to Technology@lemmy.worldEnglish · 4 months agoResearchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious querieswww.tomshardware.comexternal-linkmessage-square25fedilinkarrow-up1298arrow-down14
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 · 4 months agomessage-square25fedilink
minus-squareoDDmON@lemmy.worldlinkfedilinkEnglisharrow-up58·4 months ago …researchers from NTU were working on Masterkey, an automated method of using the power of one LLM to jailbreak another. Or: welcome to where AI becomes an arms race.
minus-squareLazaroFilm@lemmy.worldlinkfedilinkEnglisharrow-up8·4 months agoThis is how skyNet starts.
Or: welcome to where AI becomes an arms race.
This is how skyNet starts.