Once a year, a group of computer scientists and technology mavens gather at the Loebner Prize Competition to test the continuing evolution of artificial intelligence. The contest is a real-world rendition of the famous "Turing test" dreamed up by computer science luminary Alan Turing in the 1950s: A human engages in an electronic conversation with another human and a machine simultaneously. If the judge can't tell the person from the computer, then the machine passes.
The annual winner of the competition walks away with a $2,000 prize and a bronze medal. The Grand Prize of $100,000 and a Gold Medal has never been awarded, and remains reserved for the first computer whose responses are fully indistinguishable from a human's—the first computer that can truly "think" (at least, per Turing's definition).
Last year's judges—a group of journalists, computer scientists, philosophy professors, and other academics—each sat at a computer screen split down the middle, with one chat on each side. The judges were told that one of the chats was with a bot, while the other was with a human.
First prize went to Elbot, the brainchild of Fred Roberts and Artificial Solutions, a company that creates customer service bots for businesses like Ikea and Telenor, the Norway-based telecom company. The machine fooled 25 percent of the judges. Second prize went to Eugene Goostman, a bot created by the Eastern European team of Vladimir Veselov, Eugene Demchenko, and Sergey Ulasen. It fooled about 10 percent of the judges.
So what, based on the most recent test, are the surefire ways to spot a bot? We asked Loebner Prize organizer Kevin Warwick, a computer science expert and head of the cybernetics department at Reading University, to share his best tips.
