LughMA to FuturologyEnglish · 10 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.comLughMA to FuturologyEnglish · 10 months agomessage-square9fedilink
minus-squaremateomaui@reddthat.comlinkfedilinkEnglisharrow-up2·10 months agoAlright, I’ll switch to digging holes for the family burial ground.
Alright, I’ll switch to digging holes for the family burial ground.