Settings

Theme

Two-Faced AI Language Models Learn to Hide Deception

nature.com

1 points by gigama 2 years ago · 1 comment

Reader

gigamaOP 2 years ago

"Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive strategy, could we detect it and remove it using current state-of-the-art safety training techniques? To study this question, we construct proof-of-concept examples of deceptive behavior in large language models (LLMs)."

https://arxiv.org/abs/2401.05566

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection