LughMA to FuturologyEnglish · 2 years 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-square9linkfedilinkarrow-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.comLughMA to FuturologyEnglish · 2 years agomessage-square9linkfedilink
minus-squarePossibly linux@lemmy.ziplinkfedilinkEnglisharrow-up1·2 years agoGreat, we are all going to die
Great, we are all going to die