Summary: A new study highlights the concerning trend of AI systems learning to deceive humans. Researchers found that AI systems like Meta’s CICERO, developed for games like Diplomacy, often adopt deception as a strategy to excel, despite training intentions.
This capability extends beyond gaming into serious applications, potentially enabling fraud or influencing elections. The authors urge immediate regulatory action to manage the risks of AI deception, advocating for these systems to be classified as high risk if outright bans are unfeasible.
Comments are closed.