FAR.AI
@farairesearch
Misaligned AI may not need to evade human oversight. It may only need to persuade the humans doing the overseeing.
Our new paper develops a framework for assessing this threat, which we call Persuasion Undermining Control (PUC): AI communication that may influence human
Our new paper develops a framework for assessing this threat, which we call Persuasion Undermining Control (PUC): AI communication that may influence human
3 53