Minds and Machines

, Volume 20, Issue 3, pp 441–454

Hidden Interlocutor Misidentification in Practical Turing Tests

Article

DOI: 10.1007/s11023-010-9219-6

Cite this article as:
Shah, H. & Warwick, K. Minds & Machines (2010) 20: 441. doi:10.1007/s11023-010-9219-6

Abstract

Based on insufficient evidence, and inadequate research, Floridi and his students report inaccuracies and draw false conclusions in their Minds and Machines evaluation, which this paper aims to clarify. Acting as invited judges, Floridi et al. participated in nine, of the ninety-six, Turing tests staged in the finals of the 18th Loebner Prize for Artificial Intelligence in October 2008. From the transcripts it appears that they used power over solidarity as an interrogation technique. As a result, they were fooled on several occasions into believing that a machine was a human and that a human was a machine. Worse still, they did not realise their mistake. This resulted in a combined correct identification rate of less than 56%. In their paper they assumed that they had made correct identifications when they in fact had been incorrect.

Keywords

18th Loebner prize for artificial intelligence Confederate effect Elbot Eliza effect Gender-blurring effect Jury-service Parallel-paired Practical Turing tests Turing’s imitation game 

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  1. 1.School of Systems EngineeringThe University of Reading, WhiteknightsReadingUK