Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 2 年前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 · 2 年前message-square9fedilink
minus-squaremateomaui@reddthat.comlinkfedilinkEnglisharrow-up2·2 年前Alright, I’ll be out back digging the bomb shelter.
minus-squarePossibly linux@lemmy.ziplinkfedilinkEnglisharrow-up1·edit-22 年前Its too late for that honestly
minus-squaremateomaui@reddthat.comlinkfedilinkEnglisharrow-up2·2 年前Alright, I’ll switch to digging holes for the family burial ground.
Sorry, to late for that
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.