LughMA to FuturologyEnglish • 5 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-square9arrow-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 • 5 months agomessage-square9
minus-square@mateomaui@reddthat.comlinkfedilinkEnglish1•5 months agoJust… don’t hook it up to the defense grid.
minus-square@mateomaui@reddthat.comlinkfedilinkEnglish2•5 months agoAlright, I’ll be out back digging the bomb shelter.
minus-square@mateomaui@reddthat.comlinkfedilinkEnglish2•5 months agoAlright, I’ll switch to digging holes for the family burial ground.
Just… don’t hook it up to the defense grid.
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.