Jun 10, 2014

What is the “Turing test” for computers?

I heard a news segment on the radio that a computer has “passed the Turing test for the first time” but I missed any explanation on what exactly that test is. The only Turing that comes to my mind is Alan Turing, the British codebreaker who cracked the Nazi’s Enigma code device in WWII. Does it have something to do with that? What is the “Turing test” and what did a computer have to do to pass it for the first time?

Turing test

"The Turing test is a test of a machine's ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a human. In the original illustrative example, a human judge engages in natural language conversations with a human and a machine designed to generate performance indistinguishable from that of a human being. All participants are separated from one another. If the judge cannot reliably tell the machine from the human, the machine is said to have passed the test. The test does not check the ability to give the correct answer to questions; it checks how closely the answer resembles typical human answers. The conversation is limited to a text-only channel such as a computer keyboard and screen so that the result is not dependent on the machine's ability to render words into audio.[2]

The test was introduced by Alan Turing in his 1950 paper "Computing Machinery and Intelligence," which opens with the words: "I propose to consider the question, 'Can machines think?'" Because "thinking" is difficult to define, Turing chooses to "replace the question by another, which is closely related to it and is expressed in relatively unambiguous words."[3] Turing's new question is: "Are there imaginable digital computers which would do well in the imitation game?"[4] This question, Turing believed, is one that can actually be answered. In the remainder of the paper, he argued against all the major objections to the proposition that "machines can think".[5]"

Essentially, the Turing test requires a computer to fool a human into erroniously believing the computer is also a human 30% of the time while engaging in 5 minutes of keyboard conversation. 


One of the more entertaining articles I’ve read about this was by Mike Masnick at techdirt. He points out that (1) this was not a supercomputer but a chatbot. A. Chatbot. (2) It wasn’t even a particularly good chatbot; other chatbots have passed the “Turing test” in the past with better numbers. To put the cherry on top, Masnick links to all the articles that pretty much...or completely...got the story wrong. 


Answer this