Computers still not quite clever enough to fool humans, Turing Test shows
Last Updated: 5:01pm BST 12/10/2008
Computers are still not quite good enough to pass themselves off as human, a test has shown.
But science fact almost caught up with science fiction when six computers came close to passing a major artificial intelligence milestone by holding a conversation with a person. In a breakthrough hailed as the most significant since a computer beat chess champion Garry Kasparov in 1997, the machines came the closest yet to imitating a real-time “chat”.
In an experiment known as the Turing Test after the great British mathematician Alan Turing, the six Artificial Conversational Entities (ACEs) tried to fool human interrogators into thinking they were also human. All the ACEs managed to fool at least one of their human interrogators and organisers feel it will only be a matter of time before the test is passed. But none could pass the threshold set by Turing in 1950 of fooling 30 per cent of the human interrogators.
The winning machine, known as Elbot, could only achieve a 25 per cent success rate. Professor Kevin Warwick from the University of Reading’s School of Systems Engineering, who organised the test, said: “This has been a very exciting day with two of the machines getting very close to passing the Turing Test for the first time.
“In hosting the competition here, we wanted to raise the bar in Artificial Intelligence and although the machines aren’t yet good enough to fool all of the people all of the time, they are certainly at the stage of fooling some of the people some of the time.
“Today’s results actually show a more complex story than a straight pass or fail by one machine. Where the machines were identified correctly by the human interrogators as machines, the conversational abilities of each machine was scored at 80 and 90%.
Here is the full article.
It’s still smarter than all the loons from the USCF.
They certainly fooled all the arbiters and Topalov when Kramnik used it in his match!