X

Computer program fools humans, allegedly passes Turing test

A team in Russia claims its chatbot managed to dupe more than 30 percent of human interrogators into believing it's human. Are they to be believed?

Chris Matyszczyk
3 min read

eugenev2.jpg
Real or fake? Eugene Goostman

It wasn't Siri, nor a souped-up Scarlett Johansson.

However, it seems that artificial intelligence may have gone even further toward a time when it will fool us that it's just like us. Emphasis on the "may have."

A Russia-based team claims to be the first to create a program that passed the Turing test. Named after Alan Turing -- who died on June 7, 1954 -- the challenge is to persuade a minimum of 30 percent of humans that the computer program is a real person.

As the Independent reported, in tests conducted at the Royal Society in London, the Eugene Goostman program managed to persuade 33 percent of people that it was a 13-year-old boy from Odessa, Ukraine.

The event was organized by the University of Reading. The university insisted that this is the first time the Turing test has been passed with flying deception.

Professor Ken Warwick, a visiting professor at Reading, said in a press release: "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."

There's a certain convenience in pretending you're a 13-year-old boy, of course. You can fool people more easily because, unlike IBM's Watson, you don't have to pretend you know everything. Rather you have to have a very well-designed "dialog controller."

The man behind the boy, Vladimir Veslov, explained: "This year we improved the 'dialog controller,' which makes the conversation far more human-like when compared to programs that just answer questions. Going forward we plan to make Eugene smarter and continue working on improving what we refer to as 'conversation logic'."

Some will be perturbed that computers are becoming this wise. The opportunities for online fraud will surely be increased.

(Turns out, some who participated in the contest are perturbed by the university's claims, according to a story in the Guardian Monday. "It has kept some -- not all -- who try it out entertained for more than five minutes," Aaron Sloman, a professor at Birmingham University who was a judge at the event, told the Guardian. "But it is essentially stupid and incompetent, no matter how many people it fools for how long.")

Those who are gullible to such things, though, are often those who think nothing right now of sending an online date whom they have never met huge sums of money.

The woman who was duped into wiring $500,000 to someone she'd met on a Christian dating site is but one example.

It's true, though, that as AI progresses, we'll be forced to think at least twice when meeting "people" online.

It's one more complication in an already mentally challenging world.

I wonder what Turing would have made of it all.

Updated, June 9 at 4:18 p.m. PT: The headline and story have been changed to reflect that some doubt has been cast on whether the program actually passed the Turing test.