Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 10 个月前Two-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 · 10 个月前message-square9fedilink
minus-squaremateomaui@reddthat.comlinkfedilinkEnglisharrow-up2·10 个月前Alright, I’ll be out back digging the bomb shelter.
minus-squarePossibly linux@lemmy.ziplinkfedilinkEnglisharrow-up1·edit-210 个月前Its too late for that honestly
minus-squaremateomaui@reddthat.comlinkfedilinkEnglisharrow-up2·10 个月前Alright, I’ll switch to digging holes for the family burial ground.
Alright, I’ll be out back digging the bomb shelter.
Its too late for that honestly
Alright, I’ll switch to digging holes for the family burial ground.