WASHINGTON, D.C. – Experts have long warned about the threat posed by artificial intelligence going rogue, but a new research paper suggests it is already happening.Current 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, a team of scientists argue in the journal Patterns on Friday.
ChatGPT’s logo is seen on a laptop screen and the letters ‘AI’ are seen on a smartphone screen in the city of Frankfurt, western Germany on Nov. 23, 2023. AFP FILE PHOTO'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.