They can outwit humans at board games, decode the structure of proteins and hold a passable conversation, but as AI systems have grown in sophistication so has their capacity for deception, scientists warn.

The analysis, by Massachusetts Institute of Technology (MIT) researchers, identifies wide-ranging instances of AI systems double-crossing opponents, bluffing and pretending to be human. One system even altered its behaviour during mock safety tests, raising the prospect of auditors being lured into a false sense of security.

“As the deceptive capabilities of AI systems become more advanced, the dangers they pose to society will become increasingly serious,” said Dr Peter Park, an AI existential safety researcher at MIT and author of the research.

Park was prompted to investigate after Meta, which owns Facebook, developed a program called Cicero that performed in the top 10% of human players at the world conquest strategy game Diplomacy. Meta stated that Cicero had been trained to be “