The Turing Test

Devised by the mathematician Alan Turing in 1950 in his paper "Computing Machinery and Intelligence,” the Turing Test is considered the gold standard for gauging how far we’ve come in the field of artificial intelligence. The test is named after Turing, but the roots of the it go back to René Descartes in the 17th century. It strikes not only at questions of artificial intelligence, but also at the limits of automata in general, the question of how we know if other people possess consciousness, and even the philosophical basis of materialism.

The idea is that an interrogator communicates with two contestants, one human and the other a machine, solely by text. The interrogator asks questions of each for five minutes and then decides which one is human. If the machine wins more the 30 percent of the rounds, it’s regarded as having passed the test. So far, no computer program has ever achieved this, but on Saturday, the chatbot Eugene Goostman scored 33 percent.

Break on thru to the other side - Jim Morrison/The Doors

Addendum: Turing's amazing article, Computing Machinery and Intelligence will blow you away with just how prescient it truly was in defining how computing and AI could evolve using the test as a means to make it happen.