TootSweet@lemmy.worldM to Fuck AI@lemmy.worldEnglish · 9 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-up1182arrow-down10
arrow-up1182arrow-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 · 9 hours agomessage-square18fedilink
minus-squarexxce2AAb@feddit.dklinkfedilinkarrow-up6·9 hours agoPlease don’t tempt me with a good time.
Please don’t tempt me with a good time.