Researchers find instances of systems double-crossing opponents, bluffing, pretending to be human and modifying behaviour in tests
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.
About Author
More Stories
Male mosquitoes to be genetically engineered to poison females with semen in Australian research
Breakthrough drugs herald ‘new era’ in battle against dementia, experts predict
Memo to Trump: US telecoms is vulnerable to hackers. Please hang up and try again | John Naughton