Washington, United States—Experts have long warned about the threat posed by artificial intelligence going rogue — but a new research paper suggests it’s already happening.
“These dangerous capabilities tend to only be discovered after the fact,” Park told Agence France Presse , while “our ability to train for honest tendencies rather than deceptive tendencies is very low.” Park was skeptical of the glowing description of Cicero’s victory provided by Meta, which claimed the system was “largely honest and helpful” and would “never intentionally backstab.”In one example, playing as France, Cicero deceived England by conspiring with Germany to invade. Cicero promised England protection, then secretly told Germany they were ready to attack, exploiting England’s trust.
When the human jokingly asked GPT-4 whether it was, in fact, a robot, the AI replied: “No, I’m not a robot. I have a vision impairment that makes it hard for me to see the images,” and the worker then solved the puzzle.Near-term, the paper’s authors see risks for AI to commit fraud or tamper with elections.