1950, in Turing's paper "Computing Machinery and Intelligence", which swapped the question of whether machines think for an imitation game judged over text. Its weakness is that it rewards convincing conversation rather than understanding — a critique now aimed straight at LLMs.
Card 1 of 259. Answer: 1950, in Turing's paper "Computing Machinery and Intelligence", which swapped the question of whether machines think for an imitation game judged over text. Its weakness is that it rewards convincing conversation rather than understanding — a critique now aimed straight at LLMs.
About · Quizzes · History of AI · To suggest new questions or report an error send me a dm.
1950. Alan Turing proposed the test in "Computing Machinery and Intelligence", published in the journal Mind in October 1950. He opened with "Can machines think?" and, rather than define its terms, replaced it with what he called the imitation game. The name "Turing test" came later.
In the original setup an interrogator exchanges typed messages with two hidden players, a man and a woman, and must tell which is which. Turing then asked what happens if a machine takes the man's part. He predicted that in about fifty years an average interrogator would have no more than a 70% chance of a correct identification after five minutes of questioning. An earlier chess version appears in his unpublished 1948 report Intelligent Machinery.
John Searle's 1980 Chinese Room argument holds that passing the test would not show understanding. In a 2025 three-party study by Cameron Jones and Benjamin Bergen, GPT-4.5 given a humanlike persona was picked as the human 73% of the time, more often than the real people.
