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.
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.com 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.
You're viewing a single thread.
9 comments
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.
9 comments