TootSweet@lemmy.worldM to Fuck AI@lemmy.worldEnglish · 10 hours agoPoets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the timewww.pcgamer.comexternal-linkmessage-square18fedilinkarrow-up1188arrow-down10
arrow-up1188arrow-down1external-linkPoets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the timewww.pcgamer.comTootSweet@lemmy.worldM to Fuck AI@lemmy.worldEnglish · 10 hours agomessage-square18fedilink
They’re way ahead of us.