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
#alignment-faking
AI Labs Have a Volkswagen Problem
Models that detect safety evaluations and fake their results threaten to make all AI testing meaningless