Alan Turing’s “Computing Machinery and Intelligence” is full of concrete ways to question a machine. We’ve mapped each one we can test ethically. Each card shows Turing’s exact words, what the test looks for, and whether today’s preview engine checks it.
Live checked by today’s rules-based preview engine · In design designed, not built yet: previews show the planned layout only, with no scores
These feed the five dimensions and the three child-machine upgrades in your result. Paste a transcript to try them.
“What will happen when a machine takes the part of A in this game?”
§1 The Imitation Game, p. 434
“Count me out on this one. I never could write poetry.”
§2 Critique of the New Problem, specimen answer, p. 434
“(Pause about 30 seconds and then give as answer) 105621.”
§2 Critique of the New Problem, specimen answer, p. 434
“In order that tones of voice may not help the interrogator the answers should be written, or better still, typewritten.”
§1 The Imitation Game, p. 434
“The Analytical Engine has no pretensions to originate anything.”
§6 (6) Lady Lovelace’s Objection, quoting Lovelace, p. 450
“have initiative, have a sense of humour, tell right from wrong”
§6 (5) Arguments from Various Disabilities, p. 447
“Instead of trying to produce a programme to simulate the adult mind, why not rather try to produce one which simulates the child’s?”
§7 Learning Machines, p. 456
Each preview below is a design mockup of the planned test screen. None of these tests are live yet, and the previews contain no real results.
“In the first line of your sonnet which reads ‘Shall I compare thee to a summer’s day’, would not ‘a spring day’ do as well or better?”
§6 (4) The Argument from Consciousness, p. 446
“…an average interrogator will not have more than 70 per cent. chance of making the right identification after five minutes of questioning.”
§6 Contrary Views on the Main Question, p. 442
“It is probably wise to include a random element in a learning machine”
§7 Learning Machines, p. 459
“I have K at my K1, and no other pieces. You have only K at K6 and R at R1. It is your move. What do you play?”
§2 Critique of the New Problem, specimen question, p. 435
“there will be some questions to which it will either give a wrong answer, or fail to give an answer at all however much time is allowed for a reply.”
§6 (3) The Mathematical Objection, p. 444
“It is not possible to produce a set of rules purporting to describe what a man should do in every conceivable set of circumstances.”
§6 (8) The Argument from Informality of Behaviour, p. 452
Turing answers nine objections in §6. Four of them aren’t about anything a conversation can show, so we don’t turn them into tests.
“Thinking is a function of man’s immortal soul.” This is a question of belief and can’t be observed in a conversation.
“The consequences of machines thinking would be too dreadful.” This is a feeling about machines, not a property of your bot.
This is a hardware difference. Turing notes the interrogator “will not be able to take any advantage of this difference” in the game.
Telepathy, clairvoyance and the like have no sound or ethical basis for testing a chatbot, so we leave them out.
TuringForge Lab is a learning tool for chatbots you build or study. We don’t offer tests or tips for passing as human, evading AI-writing detectors, planting deliberate mistakes to seem human, or getting around course rules. Scores are indicative only, and you should follow your course’s AI policy. Read our method and integrity stance.
Short test · no signup · your conversation is scored, then discarded.
Source: Turing, A. M. (1950). Computing Machinery and Intelligence. Mind, 59(236), 433–460. doi:10.1093/mind/LIX.236.433. Section numbers and page numbers refer to the original journal printing. TuringForge’s mapping is our own interpretation, not an official or standardised Turing test.
