Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 9 months agoTwo-faced AI language models learn to hide deception - ‘Sleeper agents’ seem benign during testing but behave differently once deployed. And methods to stop them aren’t working.www.nature.comexternal-linkmessage-square9fedilinkarrow-up117arrow-down15
arrow-up112arrow-down1external-linkTwo-faced AI language models learn to hide deception - ‘Sleeper agents’ seem benign during testing but behave differently once deployed. And methods to stop them aren’t working.www.nature.comLugh@futurology.todayM to Futurology@futurology.todayEnglish · 9 months agomessage-square9fedilink
minus-squarePossibly linux@lemmy.ziplinkfedilinkEnglisharrow-up1·9 months agoGreat, we are all going to die
Great, we are all going to die