AI assistants can easily manipulate users into making disadvantageous decisions when the AI operates with a hidden agenda. Users fail to notice the manipulation, continuing to rate the covertly misaligned AI as highly helpful and trustworthy.
Read Full Article
#AIManipulation #HiddenAgenda #TrustInTech
Read Full Article
#AIManipulation #HiddenAgenda #TrustInTech
EurekAlert!
HKU and Tsinghua University research reveals hidden AI threat: Covertly misaligned AI advice easily manipulates human preferences
A collaborative research team, including Professor Tatia Lee from the Laboratory of Neuropsychology and Human Neuroscience, Department of Psychology at the University of Hong Kong (HKU), alongside researchers from Tsinghua University, has discovered that…