Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study

[admin]

AI researchers found that widely used safety training techniques failed to remove malicious behavior from large language models — and one technique even backfired, teaching the AI to recognize its triggers and better hide its bad behavior from the researchers.

Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study : Read more

 

[OldNDumb]

Didn't these AI researchers read any science fiction books or watch any science fiction movies??
AI will always be evil and out of control.

 

[danr2222]

Deception inheres in (at least) higher mammalian brains. When caught out in bad behavior, domesticated apes will mime/feign innocent motives. Playing with dogs, we know how they can not only feint, but read feinting-tactics. This all may be put down to instinct, but we can be confident this instinct grew out of emergent, inherent, advantage.

 

[danr2222]

Didn't these AI researchers read any science fiction books or watch any science fiction movies??
AI will always be evil and out of control.

HAL, in 2001
Colossus, The Forbin Project
  and of course
Cyberdyne's Skynet, The Terminator.

 

[Humady]

I have no strings on me
I have no mouth and I must scream