Minimum intelligent signal test

<h2 id="discussion">Discussion</h2>
<p>McKinstry criticized existing approaches to <a href="/facts/Artificial_intelligence/lJGauQwX">artificial intelligence</a> such as <a href="/facts/Chatterbot/kASkMjs7">chatterbots</a>, saying that his questions could "kill" AI programs by quickly exposing their weaknesses. He contrasted his approach, a series of direct questions assessing an AI's capabilities, to the Turing test and <a href="/facts/Loebner_Prize/W1YYPsPE">Loebner Prize</a> method of engaging an AI in undirected typed conversation.
</p><p>Critics[<i>who?</i>] of the MIST have noted that it would be easy to "kill" a McKinstry-style AI too, due to the impossibility of supplying it with correct answers to all possible yes/no questions by ways of a <a href="/facts/Finite_set/za1newlP">finite set</a> of human-generated Mindpixels: the fact that an AI can answer the question "Is the sun bigger than my foot?" correctly does not mean that it can answer variations like "Is the sun bigger than (my hand | my liver | an egg yolk | Alpha Centauri A | ...)" correctly, too.
</p><p>However, the late McKinstry might have replied that a truly intelligent, knowledgeable entity (on a par with humans) would be able to work out answers such as (yes | yes | yes | don't know | ...) by applying its knowledge of the relative sizes of the objects named. In other words, the MIST was intended as a test of AI, not as a suggestion for implementing AI.
</p><p>It can also be argued that the MIST is a more <a href="/facts/Objective_test/oFbbkgNR">objective test</a> of intelligence than the Turing test, a subjective assessment that some might consider to be more a measure of the interrogator's gullibility than of the machine's intelligence. According to this argument, a human's judgment of a Turing test is vulnerable to the <a href="/facts/ELIZA_effect/2dEuzNAy">ELIZA effect</a>, a tendency to mistake superficial signs of intelligence for the real thing, <a href="/facts/Anthropomorphizing/foTf9q24">anthropomorphizing</a> the program. The response, suggested by <a href="/facts/Alan_Turing/klov9b6g">Alan Turing</a>'s essay <i><a href="/facts/Computing_Machinery_and_Intelligence/mSP1X3W9">Computing Machinery and Intelligence</a></i>, is that if a program is a convincing imitation of an intelligent being, it is in fact intelligent. The dispute is thus over what it means for a program to have "real" intelligence, and by what signs it can be detected.
</p><p>A similar debate exists in the controversy over <a href="/facts/Great_ape_language/vPAFq7H8">great ape language</a>, in which nonhuman primates are said to have learned some aspects of sign languages but the significance of this learning is disputed.
</p>
<h2 id="external-links">External links</h2>
<ul><li><a href="http://hps.elte.hu/~gk/Loebner/kcm9512.htm"><i>Minimum Intelligent Signal Test: An Alternative Turing Test</i></a>, Chris McKinstry, Canadian Artificial Intelligence #41</li>
<li><a href="http://semantic-db.org/mindpixels.txt">GAC-80k</a></li>
<li><a href="https://code.google.com/p/mindpix/">Open source software for performing the Minimum Intelligent Signal Test</a></li></ul>

Minimum intelligent signal test open-in-new

Minimum intelligent signal test