In 1950, Alan Turing, widely considered to be one of the founding fathers of computer science, proposed a method for determining whether machines can behave intelligently. That method has come to be known as the Turing test. This past Saturday, at Turing Test 2014, an event organized by the University of Reading in the UK, a program called "Eugene Goostman" passed the test in what the event's organizers call a world first.
In order to pass the test, the rules of the event say a program must be mistaken for a human more than 30% of the time during a series of five-minute conversations with human judges. Eugene convinced its interrogators that it was human 33% of the time. No computer program had been able to pass the test until now, according to the university's press release. Professor Kevin Warwick, one of the organizers of the event, described the stringent standards that were applied in order to reach this conclusion:
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.
Eugene was developed in St. Petersburg, Russia by a team that includes Vladimir Veselov, the program's creator. Veselov had this to say after the competition:
I want to congratulate everyone who worked on Eugene Goostman. Our whole team is very excited with this result. It's a remarkable achievement for us and we hope it boosts interest in artificial intelligence and chatbots.
Update 6/10: A number of websites, including Techdirt, have noted that Professor Kevin Warwick is notorious for carrying out PR stunts that resemble scientific achievements. It would probably be best to take this news with a grain of salt until the methodology and results are independently verified. The publicly available version of Eugene also doesn't appear to be very convincing as a conversation partner.
|Friday night topic: quadcopters!||20|
|The TR Podcast video 173: Torquing the Titan||1|
|Report: AMD R&D spending falls to near-10-year low||77|
|Deal of the week: Ultra-wide IPS for $750, 16GB DDR4-2666 for $190, plus more||47|
|Broadwell Xeon D lands on Mini-ITX boards||34|
|Half-Life 2: Update mod adds modern polish to old classic||57|
|The TR Podcast is live, so come ask us stuff!||1|
|AMD shows off DirectX 12 performance with new 3DMark benchmark||84|