Can machines think? A report on Turing test experiments at the Royal Society. Issue 6 (1st November 2016)

• Record Type: Journal Article
• Authors: Warwick, Kevin; Shah, Huma
• Is Part Of: Journal of experimental & theoretical artificial intelligence. Volume 28:Issue 6(2016)
• Page Start: 989
• Page End: 1007
• Publication Date: 2016-11-01
• Subjects: deception detection -- natural language -- Turing's imitation game -- chatbots -- machine misidentification; Artificial intelligence -- Periodicals; 006.3
• DOI: 10.1080/0952813X.2015.1055826
• Languages: English
• ISSNs: 0952-813X

Abstract

Abstract : In this article we consider transcripts that originated from a practical series of Turing's Imitation Game that was held on 6 and 7 June 2014 at the Royal Society London. In all cases the tests involved a three-participant simultaneous comparison by an interrogator of two hidden entities, one being a human and the other a machine. Each of the transcripts considered here resulted in a human interrogator being fooled such that they could not make the 'right identification', that is, they could not say for certain which was the machine and which was the human. The transcripts presented all involve one machine only, namely 'Eugene Goostman', the result being that the machine became the first to pass the Turing test, as set out by Alan Turing, on unrestricted conversation. This is the first time that results from the Royal Society tests have been disclosed and discussed in a paper.