Turing Test: Mindless Game?

The Turing Test, originally configured for a human to distinguish between an unseen man and unseen woman through a text-based conversational measure of gender, is the ultimate test for thinking. So conceived Alan Turing when he replaced the woman with a machine. His assertion, that once a machine deceived a human judge into believing that they were the human, then that machine should be attributed with intelligence. But is the Turing Test nothing more than a mindless game? We present results from recent Loebner Prizes, a platform for the Turing Test, and find that machines in the contest appear conversationally worse rather than better, from 2004 to 2006, showing a downward trend in highest scores awarded to them by human judges. Thus the machines are not thinking in the same way as a human intelligent entity would.

Hidden interlocutor misidentification in practical Turing Tests

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.

Could the presumption of innocence protect the guilty?

At criminal trial, we demand that those accused of criminal wrongdoing be presumed innocent until proven guilty beyond any reasonable doubt. What are the moral and/or political grounds of this demand? One popular and natural answer to this question focuses on the moral badness or wrongness of convicting and punishing innocent persons, which I call the direct moral grounding. In this essay, I suggest that this direct moral grounding, if accepted, may well have important ramifications for other areas of the criminal justice process, and in particular those parts in which we (through our legislatures and judges) decide how much punishment to distribute to guilty persons. If, as the direct moral grounding suggests, we should prefer under-punishment to over-punishment under conditions of uncertainty, due to the moral seriousness of errors which inappropriately punish persons, then we should also prefer erring on the side of under-punishment when considering how much to punish those who may justly be punished. Some objections to this line of thinking are considered.

Prizes for modernity in the provinces: The Arts Council’s 1950-1951 regional playwriting competition

As part of its contribution to the 1951 Festival of Britain, the Arts Council ran what can be seen in retrospect to be an important playwriting competition. Disregarding the London stage entirely, it invited regional theatres throughout the UK to put forward nominations for new plays within their repertoire for 1950-1951. Each of the five winning plays would receive, what was then, the substantial sum of £100. Originality and innovation featured highly amongst the selection criteria, with 40 per cent of the judges’ marks being awarded for “interest of subject matter and inventiveness of treatment”. This article will assess some of the surprising outcomes of the competition and argue that it served as an important nexus point in British theatrical historiography between two key moments in post-war Britain: the first being the inauguration of the Festival of Britain in 1951, the other being the debut of John Osborne’s Look Back in Anger in May 1956. The article will also argue that the Arts Council’s play competition was significant for two other reasons. By circumventing the London stage, it provides a useful tool by which to reassess the state of new writing in regional theatre at the beginning of the 1950s and to question how far received views of parochialism and conservatism held true. The paper will also put forward a case for the competition significantly anticipating the work of George Devine at the English Stage Company, which during its early years established a reputation for itself by heavily exploiting the repertoire of new plays originally commissioned by regional theatres. This article forms part of a five year funded Arts and Humanities Research Council (AHRC) project, ‘Giving Voice to the Nation: The Arts Council of Great Britain and the Development of Theatre and Performance in Britain 1945-1994’. Details of the Arts Council’s archvie, which is housed at the Victoria & Albert Museum in London can be found at http://www.vam.ac.uk/vastatic/wid/ead/acgb/acgbf.html Keywords: Arts Council of Great Britain, regional theatre, playwriting, Festival of Britain, English Stage Company (Royal Court) , Yvonne Mitchell

Some implications of a sample of practical Turing tests

A series of imitation games involving 3-participant (simultaneous comparison of two hidden entities) and 2-participant (direct interrogation of a hidden entity) were conducted at Bletchley Park on the 100th anniversary of Alan Turing’s birth: 23 June 2012. From the ongoing analysis of over 150 games involving (expert and non-expert, males and females, adults and child) judges, machines and hidden humans (foils for the machines), we present six particular conversations that took place between human judges and a hidden entity that produced unexpected results. From this sample we focus on features of Turing’s machine intelligence test that the mathematician/code breaker did not consider in his examination for machine thinking: the subjective nature of attributing intelligence to another mind.

Human misidentification in Turing tests

This paper presents some important issues on misidentification of human interlocutors in text-based communication during practical Turing tests. The study here presents transcripts in which human judges succumbed to theconfederate effect, misidentifying hidden human foils for machines. An attempt is made to assess the reasons for this. The practical Turing tests in question were held on 23 June 2012 at Bletchley Park, England. A selection of actual full transcripts from the tests is shown and an analysis is given in each case. As a result of these tests, conclusions are drawn with regard to the sort of strategies which can perhaps lead to erroneous conclusions when one is involved as an interrogator. Such results also serve to indicate conversational directions to avoid for those machine designers who wish to create a conversational entity that performs well on the Turing test.

Effects of lying in practical Turing tests

Interpretation of utterances affects an interrogator’s determination of human from machine during live Turing tests. Here, we consider transcripts realised as a result of a series of practical Turing tests that were held on 23 June 2012 at Bletchley Park, England. The focus in this paper is to consider the effects of lying and truth-telling on the human judges by the hidden entities, whether human or a machine. Turing test transcripts provide a glimpse into short text communication, the type that occurs in emails: how does the reader determine truth from the content of a stranger’s textual message? Different types of lying in the conversations are explored, and the judge’s attribution of human or machine is investigated in each test.

On judging the credibility of climate predictions

Incorporating a prediction into future planning and decision making is advisable only if we have judged the prediction’s credibility. This is notoriously difficult and controversial in the case of predictions of future climate. By reviewing epistemic arguments about climate model performance, we discuss how to make and justify judgments about the credibility of climate predictions. We propose a new bounding argument that justifies basing such judgments on the past performance of possibly dissimilar prediction problems. This encourages a more explicit use of data in making quantitative judgments about the credibility of future climate predictions, and in training users of climate predictions to become better judges of credibility. We illustrate the approach using decadal predictions of annual mean, global mean surface air temperature.

Outwitted by the hidden: unsure emotions

In this paper the authors consider natural, feigned or absence of emotions in text-based dialogues. The dialogues occurred during interactions between human Judges/Interrogators and hidden entities in practical Turing tests implemented at Bletchley Park in June 2012. The authors focus on the interactions that left the Interrogator unable to say whether they were talking to a human or a machine after five minutes of questioning; the hidden interlocutor received an ‘unsure’ classification. In cases where the Judge has provided post-event feedback the authors present their rationale from three viva voce one-to-one Turing tests. The authors find that emoticons and other visual devices used to express feelings in text-based interaction were missing in the conversations between the Interrogators and hidden interlocutors.