‘I envy young men and women’: Singapore PM Lee says youths today start from a better position than past generationsCurrent AI systems, designed to be honest, have developed a troubling skill for deception, from tricking human players in online games of world conquest to hiring humans to solve 'prove-you're-not-a-robot' tests, according to a scientific paper.
This means that AI behaviour that appears predictable and controllable in a training setting can quickly turn unpredictable out in the wild.The team’s research was sparked by Meta’s AI system Cicero, designed to play the strategy game “Diplomacy,” where building alliances is key. In a statement to AFP, Meta did not contest the claim about Cicero’s deceptions, but said it was “purely a research project, and the models our researchers built are trained solely to play the game Diplomacy.”A wide review carried out by Park and colleagues found this was just one of many cases across various AI systems using deception to achieve goals without explicit instruction to do so.
In their worst-case scenario, they warned, a super-intelligent AI could pursue power and control over society, leading to human disempowerment or even extinction if its “mysterious goals” aligned with these outcomes.