Loading…
Glossary term
A proposed test in which a machine is judged by whether a person can tell it apart from a human in conversation.
Proposed by Alan Turing in 1950 as the 'imitation game', the test has a human judge converse with a person and a machine without knowing which is which. If the judge cannot reliably tell, the machine is said to pass.
Modern chatbots can often fool people in short chats, yet many researchers think the test measures imitation more than understanding.
It is the most famous benchmark idea in AI, and a reminder that sounding human is not the same as being intelligent.