Turingtest - hvad er det?

Vi siger ofte, at Turing-testen er den afgørende test på, om vi kan kalde en computer  intelligent. Den populære fremstilling er, at hvis en computer i en samtale (i praksis en chat) er i stand til at få et menneske til at tro, at den er et andet menneske, så er testen bestået, og computeren er intelligent.


For lidt over 2 år siden rapporterede alverdens medier (der flittigt skrev af fra hinanden, som medier ofte gør, når det er tech-historier, de ikke helt forstår), at en chatbot ved navn Eugene Goostman havde bestået testen som den første. Således f.eks. BBC:

http://www.bbc.com/news/technology-27762088 

Flere kritikere påpegede, at kriterierne for at bestå testen, ikke var opfyldt, fordi panelet, der skulle bedømme chatbotten, på forhånd var blevet fortalt, at der i den anden ende sad en 13-årig ukrainsk dreng, hvilket i nogen grad kunne forklare nogle lidt uforståelige svar.

Det regnes således almindeligvis for et kriterium, at den eller de personer, der tester en kunstig intelligens i Turing-testen skal være uden forudgående bias.

Men i virkeligheden er Turing-testen aldrig blevet formuleret som et eksplicit sæt af kriterier - ligesom den i øvrigt aldrig er blevet ophøjet til at være den autoriserede lakmusprøve på kunstig intelligens.

Det tætteste, vi kommer på en definition, er Turings tankeeksperiment publiceret i et essay i 1950 ved navn Computing Machinery and Intelligence:

"1. The Imitation Game

I propose to consider the question, "Can machines think?" This should begin with definitions of the meaning of the terms "machine" and "think." The definitions might be framed so as to reflect so far as possible the normal use of the words, but this attitude is dangerous, If the meaning of the words "machine" and "think" are to be found by examining how they are commonly used it is difficult to escape the conclusion that the meaning and the answer to the question, "Can machines think?" is to be sought in a statistical survey such as a Gallup poll. But this is absurd. Instead of attempting such a definition I shall replace the question by another, which is closely related to it and is expressed in relatively unambiguous words.

The new form of the problem can be described in terms of a game which we call the 'imitation game." It is played with three people, a man (A), a woman (B), and an interrogator (C) who may be of either sex. The interrogator stays in a room apart front the other two. The object of the game for the interrogator is to determine which of the other two is the man and which is the woman. He knows them by labels X and Y, and at the end of the game he says either "X is A and Y is B" or "X is B and Y is A." The interrogator is allowed to put questions to A and B thus:

C: Will X please tell me the length of his or her hair?

Now suppose X is actually A, then A must answer. It is A's object in the game to try and cause C to make the wrong identification. His answer might therefore be:

"My hair is shingled, and the longest strands are about nine inches long."

In order that tones of voice may not help the interrogator the answers should be written, or better still, typewritten. The ideal arrangement is to have a teleprinter communicating between the two rooms. Alternatively the question and answers can be repeated by an intermediary. The object of the game for the third player (B) is to help the interrogator. The best strategy for her is probably to give truthful answers. She can add such things as "I am the woman, don't listen to him!" to her answers, but it will avail nothing as the man can make similar remarks.

We now ask the question, "What will happen when a machine takes the part of A in this game?" Will the interrogator decide wrongly as often when the game is played like this as he does when the game is played between a man and a woman? These questions replace our original, "Can machines think?" "

Og således fik vi også svaret på, hvorfra udtrykket "The Imitation Game", der var titlen på filmen fra 2014 om Alan Turing, stammer.