skip to main content
article

Hidden Interlocutor Misidentification in Practical Turing Tests

Authors Info & Claims
Published:01 August 2010Publication History
Skip Abstract Section

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.

References

  1. Carpenter, R. (2009). Jabberwacky: Communication, companionship intelligence. http://www.jabber wacky.com/. Accessed October 25, 2009.Google ScholarGoogle Scholar
  2. Floridi, L., Taddeo, M., & Turilli, M. (2009). Turing's imitation game--Still an impossible challenge for all machines and some judges. An Evaluation of the 2008 Loebner Contest. Minds and Machines, 19(1), 145-150. Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. Loebner Prize (2008). Loebner prize for artificial intelligence--Home of the first Turing test. http://www.loebner.net/Prizef/. Accessed October 29, 2009.Google ScholarGoogle Scholar
  4. Roberts, F. & Gulsdorff, B. (2007). IVA2007--LNAI 4722, pp. 420-421. Google ScholarGoogle Scholar
  5. Roberts, F. (2005). The AI of elbot. Unpublished.Google ScholarGoogle Scholar
  6. Roberts, F. (2008). A social psychological approach to dialogue simulation. Unpublished.Google ScholarGoogle Scholar
  7. Shah, H., & Henry, O. (2005). The confederate effect in human-machine textual interaction. In A. Zemliak & N. Mastorakis (Eds.), Proceedings of the 5th WSEAS international conference on information science, communications and applications (ISCA 2005), Cancun, Mexico, May 11-14, ISBN: 960-8457-22-X, pp. 109-114.Google ScholarGoogle Scholar
  8. Shah, H., & Pavlika, V. (2005). Text-based dialogical e-query systems: Gimmick or convenience? Proceedings of the 10th international conference on speech and computers (SPECOM), Patras, Greece, October 17-19, ISBN: 5-7452-0110-X, Vol. II, pp. 425-428.Google ScholarGoogle Scholar
  9. Shah, H., & Warwick, K. (2009). Emotion in the Turing test: A downward trend for machines in recent Loebner prizes. Chapter XVII (Section V). In J. Vallverdú & D. Casacuberta (Eds.), Handbook of research on synthetic emotions and sociable robotics: New applications in affective computing and artificial intelligence. USA: Information Science Reference, ISBN: 978-1-60566-354-8.Google ScholarGoogle Scholar
  10. Shah, H., & Warwick, K. (2010). Testing Turing's five minutes parallel-paired imitation game. Kybernetes, 39(3), 449-465.Google ScholarGoogle ScholarCross RefCross Ref
  11. Turing, A. M., Braithwaite, R., Jefferson, G., & Newman, M. (1952). Can automatic calculating machines be said to think? In J. Copeland (Eds.), The essential Turing--The ideas that gave birth to the computer age (pp. 487-506). Oxford: Clarendon Press.Google ScholarGoogle Scholar
  12. Turing, A. M. (1950). Computing, machinery and intelligence. Mind, LIX(236), 433-460.Google ScholarGoogle ScholarCross RefCross Ref
  13. Turing, A. M. (1948). Intelligent machinery. In B. J. Copeland (Ed.), The essential Turing--The ideas that gave birth to the computer age. Oxford: Clarendon Press, 2004.Google ScholarGoogle Scholar
  14. Turkel, S. (1997). Life on the screen-identity in the age of the internet. London: Pheonix Paperback. Google ScholarGoogle Scholar

Index Terms

  1. Hidden Interlocutor Misidentification in Practical Turing Tests
    Index terms have been assigned to the content through auto-classification.

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in

    Full Access