Turing test
In plain wordsAlan Turing's proposed test of machine intelligence: a judge holds typed conversations with a hidden person and a hidden computer, and the computer passes if the judge cannot consistently pick it out.
A behavioral criterion for machine intelligence based on the 'imitation game' described by Alan TuringAlan Turing, prop. n.: A British mathematician who worked out what computers can do in principle, helped break German codes in the Second World War, and proposed the best-known test of machine intelligence. in Computing Machinery and IntelligenceComputing Machinery and Intelligence, prop. n.: Alan Turing's 1950 essay asking whether machines can think. It proposed a conversation test in place of that question, answered objections to thinking machines and suggested that machines might learn like children. (1950). An interrogator exchanges typed messages with two hidden respondents, one human and one machine, and must decide which is which; the machine succeeds if interrogators fail to single it out with any consistency (Turing compared their error rate with that in the original man–woman version of the game). Turing offered the game as a workable substitute for the vague question of whether machines can think, and predicted that by about 2000 a computer would leave an average interrogator no better than a 70 percent chance of a correct identification after five minutes of questioning. Later variants include restricted public contests such as the Loebner PrizeLoebner Prize, prop. n.: A yearly contest, held from 1991 to 2019, in which chatbots tried to convince judges they were human in short text chats. Its grand prize was never won, and critics called it a publicity stunt., two-party versions in which a judge rates a single interlocutor, and the 'total Turing test', which adds perception and action. In a preregistered three-party study released as a preprint in 2025, a persona-prompted GPT-4.5 was judged to be the human 73 percent of the time, more often than the real humans it was paired with.
Passing a five-minute Turing test says more about fluent conversation than about general intelligence.
Origin
Turing called it the imitation game, adapting a parlor game in which a judge tries to tell a man from a woman from written answers alone. The earliest use of the eponym is not established; 'Turing's test' and 'the Turing test' were in established use in AI and philosophy writing by the 1970s.
Usage note
Critics argue that the test rewards imitation and exploits human credulity (see ELIZA effectELIZA effect, n.: Our tendency to believe that a computer understands us, cares or thinks just because it produces humanlike words, even when it is only following simple rules., Chinese roomChinese room, n.: A thought experiment: a person who knows no Chinese follows a rulebook to answer Chinese messages so well that outsiders think they understand. If the person doesn't understand, does a computer running a program?), and that it is neither necessary nor sufficient for thought. The much-publicized 2014 claim that the chatbot Eugene Goostman had passed, by convincing 33 percent of judges, was widely rejected.
Related
- Computing Machinery and IntelligenceComputing Machinery and Intelligence, prop. n.: Alan Turing's 1950 essay asking whether machines can think. It proposed a conversation test in place of that question, answered objections to thinking machines and suggested that machines might learn like children.
- Loebner PrizeLoebner Prize, prop. n.: A yearly contest, held from 1991 to 2019, in which chatbots tried to convince judges they were human in short text chats. Its grand prize was never won, and critics called it a publicity stunt.
- ELIZAELIZA, prop. n.: A 1960s computer program that chatted by turning a user's own words back into questions, like a therapist. Many users felt understood, though the program understood nothing.
- Chinese roomChinese room, n.: A thought experiment: a person who knows no Chinese follows a rulebook to answer Chinese messages so well that outsiders think they understand. If the person doesn't understand, does a computer running a program?
- artificial general intelligenceartificial general intelligence, n.: AI that could learn and do almost any mental task a capable adult can, rather than excelling at one narrow job. Experts disagree on the exact bar and on when, or whether, it will arrive.
- Alan TuringAlan Turing, prop. n.: A British mathematician who worked out what computers can do in principle, helped break German codes in the Second World War, and proposed the best-known test of machine intelligence.
- Winograd schema challengeWinograd schema challenge, prop. n.: A test of machine common sense built from pairs of sentences in which changing one word changes what a pronoun refers to — something people resolve instantly using everyday knowledge.
Sources
- Turing, A. M. (1950). Computing Machinery and Intelligence. Mind 59(236), 433–460.
- Jones, C. R. & Bergen, B. K. (2025). Large Language Models Pass the Turing Test. arXiv:2503.23674 (University of California San Diego).
Mentioned in
Alan TuringAlan Turing, prop. n.: A British mathematician who worked out what computers can do in principle, helped break German codes in the Second World War, and proposed the best-known test of machine intelligence., evaluationevaluation, n.: Testing an AI system to find out what it can and cannot do, how well, and how safely — from exam-style quizzes to hands-on trials and expert reviews., intelligenceintelligence, n.: The ability to learn, understand, reason and solve problems — especially new ones — in order to reach goals. Experts disagree about how to define it precisely, for people and even more for machines., AI-completeAI-complete, adj.: Describes a problem believed to be so hard that solving it would require general, human-level intelligence, such as flawless translation or truly understanding a story., BIG-benchBIG-bench, prop. n.: A huge collaborative test of 204 tasks, written by hundreds of researchers, built to probe what language models can and cannot do as they grow larger., CAPTCHACAPTCHA, n.: A small test on websites, like typing wavy letters or clicking every picture with a traffic light, meant to be easy for people but hard for computer programs, so as to keep automated bots out., Chinese roomChinese room, n.: A thought experiment: a person who knows no Chinese follows a rulebook to answer Chinese messages so well that outsiders think they understand. If the person doesn't understand, does a computer running a program?, Computing Machinery and IntelligenceComputing Machinery and Intelligence, prop. n.: Alan Turing's 1950 essay asking whether machines can think. It proposed a conversation test in place of that question, answered objections to thinking machines and suggested that machines might learn like children., ELIZAELIZA, prop. n.: A 1960s computer program that chatted by turning a user's own words back into questions, like a therapist. Many users felt understood, though the program understood nothing., ELIZA effectELIZA effect, n.: Our tendency to believe that a computer understands us, cares or thinks just because it produces humanlike words, even when it is only following simple rules., human-level AIhuman-level AI, n.: AI that can match an ordinary adult across the whole range of thinking tasks, such as talking, learning, reasoning and planning. An older, more intuitive name for the goal now usually called general AI., problem of other mindsproblem of other minds, n.: The puzzle of how we can know that anyone besides ourselves has thoughts and feelings, since we only ever see their behavior. AI turns this old puzzle into a practical one., Ray KurzweilRay Kurzweil, prop. n.: An American inventor of reading machines and speech technology who became the best-known prophet of the 'singularity', predicting human-level AI by 2029., Turing AwardTuring Award, prop. n.: Nicknamed the 'Nobel Prize of computing', the top honor in computer science, awarded each year since 1966 by the Association for Computing Machinery. Several AI pioneers have received it., behaviorismbehaviorism, n.: The view that the mind should be studied, or even defined, only through observable behavior rather than inner thoughts or feelings. It shapes debates about whether AI that acts intelligently really is intelligent., BlockheadBlockhead, n.: An imagined machine that passes any conversation test by looking up prewritten replies in an unimaginably huge table. Most people judge it unintelligent, which suggests that behavior alone does not prove intelligence., law of accelerating returnslaw of accelerating returns, n.: Ray Kurzweil's claim that technology improves at an ever-faster rate, because each advance helps build the next, so progress speeds up exponentially rather than steadily., Loebner PrizeLoebner Prize, prop. n.: A yearly contest, held from 1991 to 2019, in which chatbots tried to convince judges they were human in short text chats. Its grand prize was never won, and critics called it a publicity stunt., Lovelace objectionLovelace objection, n.: The argument, traced to Ada Lovelace in 1843, that computers cannot be truly creative because they can only do what they have been programmed to do., Mechanical TurkMechanical Turk, prop. n.: A famous fake chess-playing machine from 1770: a robed figure that seemed to play chess by itself but hid a human player inside. Its name now stands for 'AI' that is really people working behind the scenes., Ned BlockNed Block, prop. n.: An American philosopher who distinguished felt experience from information available for thinking, and who imagined a lookup-table machine to show that passing a conversation test need not mean intelligence., PARRYPARRY, prop. n.: An early-1970s chatbot built to talk like a psychiatric patient with paranoid schizophrenia. In tests, psychiatrists reading its conversations did little better than chance at telling it from real patients — an early Turing-test-style result., Turing trapTuring trap, n.: The risk that by building AI mainly to imitate and replace people, rather than to extend what people can do, society ends up with less widely shared prosperity and weaker bargaining power for workers., Winograd schema challengeWinograd schema challenge, prop. n.: A test of machine common sense built from pairs of sentences in which changing one word changes what a pronoun refers to — something people resolve instantly using everyday knowledge.