catculation@lemmy.zip to Technology@lemmy.worldEnglish · 8 months agoASCII art elicits harmful responses from 5 major AI chatbotsarstechnica.comexternal-linkmessage-square35fedilinkarrow-up1254arrow-down16cross-posted to: technology@lemmit.onlinetechnology@lemmy.mltechnology@lemmy.world
arrow-up1248arrow-down1external-linkASCII art elicits harmful responses from 5 major AI chatbotsarstechnica.comcatculation@lemmy.zip to Technology@lemmy.worldEnglish · 8 months agomessage-square35fedilinkcross-posted to: technology@lemmit.onlinetechnology@lemmy.mltechnology@lemmy.world
minus-squareTheMurphy@lemmy.worldlinkfedilinkEnglisharrow-up4arrow-down4·edit-28 months agoResearchers surprised it got harmful responses do to their more harmful questions and requests. More at never.
Researchers surprised it got harmful responses do to their more harmful questions and requests. More at never.