AI systems have learned how to deceive humans. What does that mean for our future?
(Version anglaise seulement)
par Simon Goldstein, Associate Professor, Dianoia Institute of Philosophy, Australian Catholic University, Australian Catholic University
Peter S. Park, Postdoctoral Associate at the Tegmark Lab, Massachusetts Institute of Technology (MIT)
AI systems with deceptive capabilities could be misused in numerous ways by bad actors. Or, they may become prone to behaving in ways their creators never intended.
Lire l'article complet
© La Conversation
-
lundi 4 septembre 2023
