Robots not capable of intelligent thought (yet)

Don't manage to trick humans in Turing Test

13 October 2008 14:51 GMT / By Katie Scott

A test created in 1950 by British Mathematician Alan Turing has proved that robots aren't yet capable of intelligent thought, though they're not far off.

The experiment at the University of Reading saw five machines pitted against each other in the test which measured how human they could be by having text-based conversations with humans.

The Turing test sees machines scored for their abilities to think intelligently, and Turing himself argued that if a machine was indistinguishable from a human, then it was "thinking".

The closest to passing the Turing Test was a robot called Elbot, who reached 5% below the pass mark, winning his creators a $3000 (£1760) prize.

To pass the test, the robots had to fool 30% of its human interrogators, which interacted with the machines using text in a 5 minute, unrestricted conversation.

"During the tests, all of the ACEs managed to fool at least one of their human interrogators", a University of Reading spokesman said.

Prof Kevin Warwick, who organised the tests, added: "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%."

"This demonstrates how close machines are getting to reaching the milestone of communicating with us in a way in which we are comfortable."

"That eventual day will herald a new phase in our relationship with machines, bringing closer the time in which robots start to play an active role in our daily lives."