oded@wisdom.weizmann.ac.IL (Oded Maler) (06/12/89)
Newsgroups: comp.ai Subject: Re: Turing Test and Subject Bias Summary: Expires: References: <> Sender: Reply-To: oded@wisdom.bitnet (Oded Maler) Followup-To: Distribution: Organization: Weizmann Inst. of Science, Dept. Of Math, Rehovot, Israel Keywords: In article <> gilbert@cs.glasgow.ac.uk (Gilbert Cockton) writes: > >Then how valid is the Turing Test? > >Just what sort of Science did young Mr. Turing have in mind when he >decided that subjective opinion could ever be a measure of system >performance? > >How do AI types *REALLY* test their systems? >-- The essence of Turing's test is in the notion of INDISTINGUISHABILITY by an observer. There is a machine in Glasgow that posts from time to time some sequences of characters that succeed in fooling me (even when I'm sober) so that I cannot distinguish it from a human local-patriotic social-science-type :-{}. Such a machine passes the Turing test. Maybe a stronger observer than myself (exponential, infinite) would have caught this imposter. Of course this is not "science" unless I augment it with statistical "objective" gadgets. BTW, Turing's test ideas had a lot of influence (so my crypto friends tell me) on various notions in Cryptography and Complexity such as interactive proofs and zero-knowledge protocols. But there you have to distinguish between someone who knows some fact and someone who doesn't, or between random and non-random, and not between intelligent and non-intelligent. Oded Maler Department of Applied Mathematics Weizmann Institute of Science Rehovot 76100, Israel (oded@wisdom.bitnet)
jwi@lzfme.att.com (Jim Winer @ AT&T, Middletown, NJ) (06/13/89)
Gilbert Cockton writes: | |Then how valid is the Turing Test? | | | |Just what sort of Science did young Mr. Turing have in mind when he | |decided that subjective opinion could ever be a measure of system | |performance? | | | |How do AI types *REALLY* test their systems? Oded Maler replies: | The essence of Turing's test is in the notion of INDISTINGUISHABILITY | by an observer. There is a machine in Glasgow that posts | from time to time some sequences of characters that succeed in fooling | me (even when I'm sober) so that I cannot distinguish it from a human | local-patriotic social-science-type :-{}. Such a machine passes the Turing | test. Maybe a stronger observer than myself (exponential, infinite) would | have caught this imposter. It is clear, based on the postings to this newsgroup, that to pass the Turing test and be indistinguishable from a human, a machine must be at the minimum, sarcastic and inane on occasion. A machine which does not exhibit emotional response or a sense of humor might be considered anti-intelligent, but certainly not human. Let us not become so serious about the bullshit we wade through that we cannot laugh at ourselves. Flaming is a strictly human activity. Jim Winer ..!lzfme!jwi I believe in absolute freedom of the press. Pax Probiscus! Sturgeon's Law (Revised): 98.89% of everything is drek (1.11% is peanut butter). Rarely able to send an email reply sucessfully. The opinions expressed here are not necessarily Those persons who advocate censorship offend my religion.
cam@edai.ed.ac.uk (Chris Malcolm cam@uk.ac.ed.edai 031 667 1011 x2550) (06/15/89)
In article <1399@lzfme.att.com> jwi@lzfme.att.com (Jim Winer @ AT&T, Middletown, NJ) writes: >It is clear, based on the postings to this newsgroup, that to pass the >Turing test and be indistinguishable from a human, a machine must be >at the minimum, sarcastic and inane on occasion. A machine which >does not exhibit emotional response or a sense of humor might be >considered anti-intelligent, but certainly not human. Let us not >become so serious about the bullshit we wade through that we cannot >laugh at ourselves. Flaming is a strictly human activity. Don't underestimate Turing! He made it clear that the machine would have to mimic human imperfections, such as making arithmetic mistakes, although, as a proper gentleman, he refrained from clarifying the possible interpretation of his paper that he considered mistakes in arithmetic to be specially characteristic of women :-) On a more serious note, Harnad has suggested that the linguistic competence required by the Turing Test will in practice be unachievable by an implementation short of a robot, i.e., a creature in a world, as opposed to a brain (or computer) in a bottle attached to a terminal. In that case, Koestler's analysis of humour suggests that you might not be able to build an intelligent robot without _necessarily_ equipping it with a sense of humour. In other words, if you want to build a machine to pass the Turing Test, it may be quite unnecessary to _simulate_ humour, etc., these things may turn out to be an essential part of the architecture, much in the same way as any decently powerful vision system will be prone to optical illusions. It's a question of how many ways there are of being intelligent (those who think intelligence is a silly concept please supply an alternative word here); maybe there's only one (I'm serious - what is the alternative to "intelligent" here?). How many ways are there of doing arithmetic? Forgetting such trivial transformations as base systems, it is a presumption of the SETI program that there is only one way - the universal language of number and logic which all industrial-quality extraterrestials (and presumably robots) _must_ understand. -- Chris Malcolm cam@uk.ac.ed.edai 031 667 1011 x2550 Department of Artificial Intelligence, Edinburgh University 5 Forrest Hill, Edinburgh, EH1 2QL, UK
donp@bucket.UUCP (Don Park) (06/18/89)
>The essence of Turing's test is in the notion of INDISTINGUISHABILITY >by an observer. There is a machine in Glasgow that posts ''''''''''''''''''''''''''''' >from time to time some sequences of characters that succeed in fooling >me (even when I'm sober) so that I cannot distinguish it from a human >local-patriotic social-science-type :-{}. Such a machine passes the Turing Is there a public access system somewhere where one could call by modem to see an example of advanced natural language parsing? Can someone suggest a good place to start for studing about NLP? Thanks, Don Park -- +------------- Bark Technologies - Don Park - Bryan Bybee ------------------+ : BBS (503)-257-3666 - VOICE (503)-246-0025 - (503)-256-2195 - Bark Tech. /\ : : Hardware - Software - IBM - TANDY COLOR COMPUTER - Support - Tech. Line \/ : +----------------- ...!tektronix!teksce!bucket!donp --------------------------+
russell@minster.york.ac.uk (06/21/89)
In article <423@edai.ed.ac.uk> Chris Malcolm writes >Koestler's analysis of humour suggests that you might not be >able to build an intelligent robot without _necessarily_ equipping it with >a sense of humour. Can this really be the case? A reading of this group would suggest that intelligent people can exist *without* a sense of humour..... :-) Russell.
GA.CJJ@forsythe.stanford.edu (Clifford Johnson) (06/23/89)
In article <614432788.987@minster.york.ac.uk>, russell@minster.york.ac.uk writes: > A reading of this group would suggest that >intelligent people can exist *without* a sense of humour..... I was once compelled to take a computer personality test, in which yes/no answers were forced (no don't know allowed) to questions including "There is life after death," "I am important," and much more personal questions too. The computer print-out was taken seriously by a court, because the computer reported that its conslusions were "valid" (even though I had answered questions I simply could not answer by tossing a coin). One of the computer's conslusions was that I had no sense of humor, which I still find amusing.
cam@edai.ed.ac.uk (Chris Malcolm cam@uk.ac.ed.edai 031 667 1011 x2550) (06/24/89)
In article <614432788.987@minster.york.ac.uk> russell@minster.york.ac.uk writes: >In article <423@edai.ed.ac.uk> Chris Malcolm writes > >>Koestler's analysis of humour suggests that you might not be >>able to build an intelligent robot without _necessarily_ equipping it with >>a sense of humour. > >Can this really be the case? A reading of this group would suggest that >intelligent people can exist *without* a sense of humour..... > Don't forget that some of the contributirs to this group are machines :-) -- Chris Malcolm cam@uk.ac.ed.edai 031 667 1011 x2550 Department of Artificial Intelligence, Edinburgh University 5 Forrest Hill, Edinburgh, EH1 2QL, UK
bwk@mbunix.mitre.org (Barry W. Kort) (06/29/89)
In article <3567@lindy.Stanford.EDU> GA.CJJ@forsythe.stanford.edu (Clifford Johnson) writes: > I was once compelled to take a computer personality test, in > which yes/no answers were forced (no don't know allowed) to > questions including "There is life after death," "I am > important," and much more personal questions too. The computer > print-out was taken seriously by a court, because the computer > reported that its conslusions were "valid" (even though I had > answered questions I simply could not answer by tossing a coin). > One of the computer's conclusions was that I had no sense of > humor, which I still find amusing. I love it. Deliciously self-referential. Perhaps the computer was projecting its own personalty onto you! :-) By the way, one of the more amusing, entertaining, and informative computer programs to map one's personality is "The Mind Mirror" by Electronic Arts. It's a repackaging of some of Timothy Leary's early work, building on the personality theories of Sullivan and Jung. This one is definitely not humorless. --Barry Kort
andrew@berlioz (Lord Snooty @ The Giant Poisoned Electric Head ) (07/07/89)
In article <58049@linus.UUCP>, bwk@mbunix.mitre.org (Barry W. Kort) writes: > In article <3567@lindy.Stanford.EDU> GA.CJJ@forsythe.stanford.edu > (Clifford Johnson) writes: > > One of the computer's conclusions was that I had no sense of > > humor, which I still find amusing. > By the way, one of the more amusing, entertaining, and informative > computer programs to map one's personality is "The Mind Mirror" > by Electronic Arts. It's a repackaging of some of Timothy Leary's > early work, building on the personality theories of Sullivan and Jung. > This one is definitely not humorless. What a pleasure to see a bit of sideways renaissance stuff here. Some day or other, we'll have to come to terms with humour as part of the ai object. I have my own ideas about it, but perhaps this is worth the odd thread. IMHO, it's what's generated when one rubs together two (or more) disparate contexts, paradigms or ideas. I think it functions rather like the popular model of sleep, in that resolution on a longer term and more submerged basis occurs after the fact. Perhaps I'm being premature; should we use comp.phil.humor? Part of the key must lie in the disparity of "disparate" as applied in the particular context. There were two old men in deckchairs...... -- ................................................................... Andrew Palfreyman I should have been a pair of ragged claws nsc!berlioz!andrew Scuttling across the floors of silent seas ...................................................................
Lord.Snooty.@.The.Giant.Poisoned.El@livewire.FIDONET.ORG (Lord Snooty @ The Giant Poisoned El) (07/08/89)
-- Lord Snooty @ The Giant Poisoned El - via FidoNet node 1:362/130.0 UUCP: ...!tiamat!livewire!Lord.Snooty.@.The.Giant.Poisoned.El INTERNET: Lord.Snooty.@.The.Giant.Poisoned.El@livewire.FIDONET.ORG
smoliar@vaxa.isi.edu (Stephen Smoliar) (07/10/89)
In article <381@berlioz.nsc.com> andrew@berlioz (Lord Snooty @ The Giant Poisoned Electric Head ) writes: >Some day or other, we'll have to come to terms with humour as part of >the ai object. I have my own ideas about it, but perhaps this is worth >the odd thread. IMHO, it's what's generated when one rubs together two >(or more) disparate contexts, paradigms or ideas. This is an approach which I believe I first saw in the beginning of Arthur Koestler's THE ACT OF CREATION. Also, Marvin Minsky wrote an essay entitled, "The Funny Thing About Thinking," which appeared in the May 1984 issue of CHEMTECH (pages 270-278). ========================================================================= USPS: Stephen Smoliar USC Information Sciences Institute 4676 Admiralty Way Suite 1001 Marina del Rey, California 90292-6695 Internet: smoliar@vaxa.isi.edu "For every human problem, there is a neat, plain solution--and it is always wrong."--H. L. Mencken