For the first time in history, a computer program has managed to be convincingly human enough to pass the Turing Test.
The Turing Test is said to be passed if a computer can hoodwink humans into believing it’s a real person more than 30 per cent of the time in a series of five minute text conversations.
And a program called “Eugene Goostman”, which pretends to be a 13-year-old boy from Ukraine, has surpassed this threshold, managing to convince 33 per cent of humans that it was a fellow human. The feat occurred on Saturday, on the 60th anniversary of Turing’s death, during an event organised by the University of Reading at the Royal Society of London. The university called it a “historic milestone” in artificial intelligence.
Professor Kevin Warwick, a visiting professor at the University of Reading (and Deputy Vice-Chancellor for Research at Coventry University), commented: “In the field of Artificial Intelligence there is no more iconic and controversial milestone than the Turing Test, when a computer convinces a sufficient number of interrogators into believing that it is not a machine but rather is a human.”
“Some will claim that the Test has already been passed. The words Turing Test have been applied to similar competitions around the world. However this event involved the most simultaneous comparison tests than ever before, was independently verified and, crucially, the conversations were unrestricted. A true Turing Test does not set the questions or topics prior to the conversations. We are therefore proud to declare that Alan Turing’s Test was passed for the first time on Saturday.”
As Warwick notes, there has certainly been some controversy surrounding this story. Some commenters have pointed out that the 30 per cent criteria is based on a remark of Turing’s which was simply a prediction for the year 2000, as opposed to any actual hard criteria.
What Turing actually said back in 1950 (via VentureBeat) was: “I believe that in about fifty years’ time it will be possible to programme computers… to make them play the imitation game so well that an average interrogator will not have more than 70 percent chance of making the right identification after five minutes of questioning.”
Nonetheless, the result is an impressive enough achievement for the creators of Eugene Goostman, a Russian development team led by Vladimir Veselov and Eugene Demchenko, who have been working on the program since 2001.
Veselov noted that the young age of their virtual personality Goostman did make it easier for them to pull the wool over human eyes. He said: “Our main idea was that he can claim that he knows anything, but his age also makes it perfectly reasonable that he doesn’t know everything. We spent a lot of time developing a character with a believable personality. This year we improved the ‘dialog controller’ which makes the conversation far more human-like when compared to programs that just answer questions.”
Professor Warwick further commented on the wider impact of having a program sophisticated enough to impersonate a human to some degree, and the implications in terms of cyber-crime. He said: “The Turing Test is a vital tool for combating that threat. It is important to understand more fully how online, real-time communication of this type can influence an individual human in such a way that they are fooled into believing something is true… when in fact it is not.”
If you want to see how Goostman works yourself, then you can actually head online here and have a chat – however, right now, the site appears to have collapsed under heavy traffic with all the media attention around this story. You might have to wait a while before you can get on…
Image Credit: Venturebeat