Chatbot attains milestone at annual Turing Test competition

Eugene Goostman, a program simulating a 13-year-old Ukrainian boy, has attained a 33% success rate at the annual RSA Turing Test competition, meaning that a third of the judges were fooled into thinking that the chatbot was actually a human being. Alan Turing's iconic test was meant to cut through the existentialist crisis in artificial intelligence about what was or wasn't "intelligence" by proposing that if a human being could not distinguish between a person and code in a blind test, the code was intelligent by human standards.

The Goostman bot enjoyed the advantage of simulating someone whose first language wasn't English, and whose apparent young age could explain a lack of nuanced reasoning and basic knowledge, so you could think of this as kind of a cheat, but it's still a very impressive feat.

Eugene Goostman, a computer programme made by a team based in Russia, succeeded in a test conducted at the Royal Society in London. It convinced 33 per cent of the judges that it was human, said academics at the University of Reading, which organised the test.

It is thought to be the first computer to pass the iconic test. Though other programmes have claimed successes, those included set topics or questions in advance.

A version of the computer programme, which was created in 2001, is hosted online for anyone talk to. (“I feel about beating the turing test in quite convenient way. Nothing original,” said Goostman, when asked how he felt after his success.)

Computer becomes first to pass Turing Test in artificial intelligence milestone, but academics warn of dangerous future [Andrew Griffin/The Independent]