The Turing test probes a machine’s capability for exhibiting intelligent behavior indistinguishable from that of a person.

1950

TURING TEST

French philosopher Denis Diderot (1713–1784) once remarked: “If they find a parrot who could answer to everything, I would claim it to be an intelligent being without hesitation.” This leads to the question: Can appropriately programmed computers be considered to be intelligent entities that “think”? In 1950, English computer scientist Alan Turing (1912–1954) attempted to answer this with his famous paper “Computing Machinery and Intelligence,” published in the journal Mind. He suggested that if a computer behaves in the same way as a human, we might as well call it intelligent, and then he proposed a special test to evaluate any given computer’s intelligence: Imagine that a computer and human respond, by text, to typed questions of human judges who cannot actually see who or what is responding. If the judges cannot distinguish the computer from the person after studying the text responses, then the computer has passed a typical version of what we refer to today as the “Turing test.”

Today, the Loebner competition is held each year, in part, to honor the computer programmers who create programs that come closest to passing the Turing test. Of course, the Turing test has stimulated much debate and controversy over the years. For example, if the computer is actually far more “intelligent” than humans, it will need to pretend to be less intelligent because the test is focused on imitating humans. As a result, devious and funny techniques that introduce typing errors, change the topic of conversation, inject jokes, ask the judges questions, and so forth were often used to fool judges. In 2014, a conversational robot developed by programmers in Russia passed a version of the test, pretending to be a thirteen-year-old Ukrainian boy named Eugene Goostman.

Another challenge to the value of the Turing test is that the level of expertise of the human judges can easily change the outcome of the test. However, whatever we think about the test’s ability to detect “intelligence,” it definitely inspires creativity in computer programmers and engineers.