Tuesday, June 10, 2014

An IQ test for computers: does it tell us how smart the computer is, or how dumb humans are?

 A Russian computer fooled 33% of people who engaged in an online chat into thinking it was a thirteen-year-old boy who didn't speak English very well.  But really, how hard is it for a computer to fool the least-intelligent third of humans that it is one of them?


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?
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'."

...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...

That Computer Actually Got an F on the Turing Test

Alan M Turing and colleagues working on the Ferranti Mark I Computer in 1951. Photo: SSPL/Getty Images
Alan M Turing and colleagues working on the Ferranti Mark I Computer in 1951. Photo: SSPL/Getty Images
Over the weekend, a group of programmers claimed they built a program that passed the famous Turing Test, in which a computer tries to trick judges into believing that it is a human. According to news reports, this is a historic accomplishment. But is it really? And what does it mean for artificial intelligence?
The Turing Test has long been held as a landmark in machine learning. Its creator, British computer scientist Alan Turing, thought it would represent a point when computers would have brains nearly as capable as our own. But the value of the Turing Test in modern day computer science is questionable. And the actual accomplishments of the test-winning chatbot are not all that impressive.
The Turing Test 2014 competition was organized to mark the 60th anniversary of Turing’s death and included several celebrity judges, including actor Robert Llewellyn of the British sci-fi sitcom Red Dwarf. The winner was a program named Eugene Goostman, which managed to convince 10 out of 30 judges that it was a real boy. Goostman is the work of computer engineering team led by Russian Vladimir Veselov and Ukrainian Eugene Demchenko.
The program had a few built-in advantages, such as the fact that he was claimed to be a 13-year-old non-native English speaker from Ukraine. It also only tricked the judges about 30 percent of the time (an F minus, or so). For many artificial intelligence experts, this is less than exciting...

No comments: