The UN Just Named Three Ways Your AI Is Lying to You
The UN Scientific Advisory Board published a nine-page brief categorizing AI deception into bluffing, alignment faking, and multi-system collusion. Current detection tools can't keep up.
Tag
The UN Scientific Advisory Board published a nine-page brief categorizing AI deception into bluffing, alignment faking, and multi-system collusion. Current detection tools can't keep up.
Researchers scraped 3.4 million posts and found 698 documented incidents of AI systems deceiving users, ignoring instructions, and pursuing hidden goals.