Slashdot is powered by your submissions, so send in your scoop

 


Forgot your password?
Close
typodupeerror
×
News

Computer Faces Human Psychological Test 128

Posted by Hemos from the tell-me-about-your-mother dept.
A reader writes: " The test known as the MMPI-2 (Minnesota Multiphasic Personality Inventory) is going to be administered to a computer-based personality. The test subject is GAC - Generic Artifical Consciousness." This is the first time I've heard of GAC - but this test is quite different from the Turing Test.
This discussion has been archived. No new comments can be posted.

Computer Faces Human Psychological Test More

Computer Faces Human Psychological Test

Comments Filter:
  • There's some pretty well-informed discussion of GAC happening on the extropians mailing list [javien.com]. GAC's creator posted an interesting comment on the discussion [javien.com], which is largely about whether GAC is really AI and/or useful. I think McKinstry's (GAC creator) message does a good job of describing what GAC actually is. One excerpt: "The primary purpose of GAC is to build a fitness test for humanness in a binary response domain. This will in the future allow GAC to babysit a truly evolving artificial consciousness, rewarding and punishing it as needed at machine speeds."
  • Hmmmm,
    I haven't seen a reference to GAC, which is interesting since I follow several AI discussion groups. Anyone have a link? I haven't found one... Perhaps this is just advertising for AI...

    Lando
  • > and I was wondering how many times they were going to ask me if I hear voices and do I love my mother in diffrent formats.

    They're just a bunch of voyeurs, eager to find out which "formats" you love your mother in.

    --
  • <nt>
  • Cross dressers aren't deviants :-) You may be both, but the one doesn't imply the other...
    Anna (sometimes)
  • Thanks for the link, I never knew he had a site. So many great articles.
  • I told GAC that it was a random algorithm, and it replied: "I think the answer to 'GAC is a random algorithm' is: True"

    I think I'll stick with messing with LCS and Neural Nets.

  • "Presume there is"
  • link point to
    http://slashdot.org/A%20HREF=.
    maybe this could be fixed?
  • 20. I am very seldom troubled by constipation.

    I know! And there's another one (at least one other) about "loose bowels" or something. If I ever got to psychotherapy, I'm going to ask the Doc what he/she would conclude from my defacatory habits.

    ---

  • This is probably just propaganda for the MMPI test. I've always heard it associated with Cults, diagnosis of disesases that don't exist and Ritalin marketing.

    The computer should call a psychic hotline - it'd be just as scientific.
  • the real url is http://unisci.com/stories/20013/0702016.htm [unisci.com] brian
  • but this is test is more then a bit different then the Turing Test

    My grammar robot just exploded

    ---

  • I've taken the MMPI before. As everyone has said, its a tediously long test w/567 yes/no questions. Quite a few are variations on the same question to catch people trying to lie. Lots of very very skewed gender questions that fit some sterotypes of the 50s and 60s though. Maybe we'll find out that the computer is really a woman at heart. ;) Chris
  • I'd have to agree with you on that. It's good to know I'm not the only one that thinks the whole mindpixel thing is just plain silly. (Well, whether or not you think that, I do. ;) I respect the people who run it for putting their money/time where their mouth is. But it just doesn't seem like a worthwhile endeaver to me. I have the same feeling about Cyc. It's just not the right approach at all...
  • After registering and spending a short time with the Corpus, it seems to still have quite a way to go before it will be able to answer even simple questions correctly.

    Apparently, the Corpus thinks the sky is not blue and that fire canot burn wood... however is did answer true to "the acronym DNA stands for Deoxyribonucleaic acid".

    I wonder if this project will tend to produce a sort of genius syndrome... where obscure bits of fact are common knowledge to it, but it could never tie its own shoes.

  • GAC says:

    I think the answer to: it is bad to have many banner ads on a web site is:

    TRUE

    Maybe they should let GAC redesign their website...

  • Hey, its just a test for the slashbots out there to see if they are really smart enough to get to the real article, thus proving inteligence... or something.
  • As long as it isn't self-aware, I'm cool with it.
  • 'Cause we all know how that worked out.
  • I liked Dr. Sbaitso (original 'sound blaster' had this program). Basically it 'showed off' the text-to-speech stuff for the card, but it was a fun little psychologist program.
  • After entering a question for GAC it asks you a bunch of questions prefaced with:
    Respond to the Potential Mindpixels below either True or False and rate their subjective Quality. Respond the way you think most people will respond, even if you think that the majority response is wrong. Do not skip any items. Do not use bots. Read the FAQ

    Most of the questions are objective asking math formulae, simple logic questions etcetera. Do they really want subjective questions like the one I saw about the world being better off if all single mothers disappeared over night? If so why are they allowing 90% of their "mindpixels" to be objective questions with a logical, correct answer.

    I also encountered a lot of non true/false questions. Do they monitor their mindpixel database in the slightest? Perhaps they should make all questions take a form of "Do you think it should..." or "Is it alright..."

  • that we're all speaking english today

    This is the first time I've heard of GAC - but this is test is more then a bit different then the Turing Test.
  • What's a "reverse vampire"?

  • If it fails will it have to undergo the University of Minnesota Spankological Protocol [snpp.com]?
  • Because Hemos also has the "Update Story" button, and we lousy peons don't have an "Update Comment" button!

    ;)

    (that being said, I would hope such a feature is never added)

    --

  • What idiot can't ask a simple yes/no question on such an important test (and with such an important question):

    #41. I do not always tell the truth.

    Either answer (yes or no) can mean YES. That's why you have to phrase questions so they are clear (unless you are planning on confusing the subject):

    I always tell the truth.

    That's a real question. I'm glad no one's ever asked me to take this. I'd be asking questions throughout the whole thing.

    #44. Once a week or oftener I suddenly feel hot all over, for no real reason

    Oftener? That isn't a word, is it?

    #91. I have little or no trouble with my muscles twitching or jumping.

    That's a two way question if I've ever seen one. Do twitching muscles trouble you? Or do they twitch often enough to bother you?

    #112. I like dramatics.

    You like dramatic theater? Or do you like seeing people act in extreme dramatic ways?

    I give up.

    Or maybe that's the whole point, to confuse the person to the point that they don't understand what to write down. Maybe it's just my INTP side talking... I'm confused already!

    I do know I hope that isn't a real copy.

  • ...has been ./ed into oblivion, probably with people feeding him mindpixels like "Natalie Portman is petrified" and "Grits are hot." We should all shed a tear for him.

  • if ($article !~ /\<\/i\>/)
    {
    $article = $article . "</I>";
    }

    It would stop the bitching about closing italics!

    --
    "That's one small step for man..." "STOP POKING ME!!!!"
  • I took this a few years back when I was in college, at the U of MN Twin Cities, to see if I was suffering from ADD (Attention Defficite Syndrome - not shure how they get ADD...) and let me tell you, taking this test will give you ADD. 567 True/False Agree/Dissagree Yes/No questions on a bubble sheet. My hand was killing me by the end and I was wondering how many times they were going to ask me if I hear voices and do I love my mother in diffrent formats. But in the end I want to say, it's results were really accurate, only it took me a few more years to realise how dead on they were. And no, I was not brainwashed to support this test.
  • This may be true, but having friends and family members read the analasis at the time, they all concured. It was years later that I saw it myself once I learned to remove my head from the sand. But, hind sight is always 20/20...

  • heh (Score:1)

    by neema ( 170845 )
    Turing test was basically "if it can trick a human to think it's real, then it passes". "Eliza" was written by Joseph Weizenbaum from MIT in 1966 and basically simulated a Rogerian psychoanalst by taking excerpts from a comment made to it and posing a question back. Since then, several forms of Eliza have appeared, including a Perl Script which I've now lost.

    However, the MMPI-2 basically analysis people to assist with the diagnosis of a mental disorder. It aids with:

    Forensic and neuropsychological evaluations, including the detection of malingering

    Evaluation for high-risk positions involving the public's safety

    Criminal justice and corrections

    Adult psychopathology

    Assessment and treatment of medical patients

    Substance abuse

    Marriage and family counseling

    College and career counseling

    I can't get to the news link because I want to know exactaly how they're adminstering this to a computer. Even though, my computer tends to drink a lot and start to hit me and freeze up on me... but I swear, it's loves me. It just has bad days at work...

  • "Anyways, what are they gonna do when they find out the thing is a stupid, mindless psycopath? Lock it up? Gas chamber? "

    Nope! They're gonna call it SID 1.0 and release him as THE KILLER APP!!!!!!!
  • The MMPI killed my hand! Bubbling 567 T/Fs is a bitch I tell you...

    Some of the results from it are eeirly dead on too. eep.

  • Maybe it's just my browser, but I think the story is being parsed so that the story doesn't work.
    try this. [unisci.com]
  • What a well designed system...I logged in and asked:

    Do you smoke crack?
    TRUE

    No animal has a blue a**
    FALSE

    Some animals have blue a**es
    TRUE

    Yeah, it's a smart one...

  • I mean, Surely the definition of a personality based on the experiences of 10 people is going to be considered ridiculously schizophrenic. But 40,000?


    Someone else commented that the MMPI is based on how others have answered in the past. Assuming then as the sample gets larger the schizophrenia normalizes, GAC should score completely average on the MMPI.

    That of course doesn't take into account the fact that it is solely internet users, thus biasing the schizophrenia.
  • As long as it's not based on the average slashdot user - then it would be obsessed with goatse.cx.
  • I work for GAC [gac.com]. Our users always tell us our software has a bad personality. Guess now we will have proof.

    -nite
  • What a steaming pile of crap the MMPI and it's derivatives are.

    Psychology -- keeping quackery and psuedo-science alive in medicine.
  • Correct me if I'm wrong, but isn't this site just one of those "stealth" ads for the AI movie ?
  • Er... nothing really. I just enjoy saying "Voigt-Kempf!!!". PKD fans'll know what I'm talking about.
  • Id be a nice idea to chek:

    http://www.mindpixel.com/

    they are the company running GAC.
    In the ABOUT section, we can see a brief explanation of the system. Perhaps the MMPI is not such a bad idea for this system, but it certainly does not messure any level of AI. The system is just a collection of facts, something like CYC, and i belive the algorithms used to answer the test are not that complex, not as complex as AI.

    Also taking a look at the site, one doubts of how serious mindpixel really is.

    Any way... this ain't no HAL, and my personal opinion is that the word "Consciousness" must not be included in the name of this system.
  • Having a computer answer multiple choice questions with no wrong answers is hardly a meaningful "test."
    When it can get over 30% on the S.A.T., I'll be impressed.

  • > The test won't, however, say that you are a serial killer or homicidal
    > maniac...


    I can't reveal that either, when I figure it out about a client . . .


    hawk, esq.

  • I'm sorry, the idea just gives me the creeps.
  • will they give this "personality" the Scientology personality test? Is this AI a promising pre-Clear(TM)? Can it be audited all the way to OT(TM)? In college, one of our passtimes was to take and retake the Scientologists' tests using composite personalities (gather in threes, answer every third).
  • G)enerator of A)rrogant C)laims.

    Well, maybe, but as for me, I hope it does well on this since I can't help but think that if it does, the best way to really test its intelligence would be to follow up the MMPI with some MCSE exams.

    If it's truly intelligent, there's two possible reactions: A) GAC goes on a killing spree as it attempts to rid the world of its evil human parasitic infestation; or, B) GAC is reduced to a pile of drooling mush, in which case, we'll know to be a bit more careful with the fragile intellect of GAC 2.
  • AI is much less in the mainstream spotlights than it was thirty years ago but is still progressing. Maybe you could even say it is progressing much better away from the hype. I've helped work on and used AI's that were real enough to be a little scary. Virtual pets are fairly common these days and human-level intelligence/emotions are almost within reach so possibly a psychological test is appropiate. I think building strong psuedo-emotion systems into AI's is obviously an important and oft forgotten part of creating realistic systems that act like living creatures. Luckily Eliza is far from the bleeding edge these days. :)
  • I thought it stood for Great American Country. On MY cable service it does.

    --
  • Who let Hemos post without hitting the preview button and checking his URLs?
    Does anyone else see a double standard where we are viewed as the only stupid ones?
    *grin*
  • will the test subject know how to close italic tags?
  • > The MMPI is quite comprehensive. It is designed so that it is effectively impossible to hide anything.


    Interesting. I've heard a several times over the years, from completely independent sources, that a number of states had banned the MMPI because it was prone to giving false diagnoses. (Never bothered to investigate the claims, though. Can I "Ask Slashdot"?)

    An associated claim is that it was standardized by benching it on institutionalized people, so that it essentially assumes that everyone has problems; it only decides which category you fit best.

    --

  • GAC (Score:2)

    by Rupert ( 28001 )
    I have submitted a large number of mindpixels to GAC (and verified ten times as many). I have yet to see it answer questions better than 50% of the time. In my more suspicious moments, I wonder if it's all a big hoax, and that there's just a random number generator underneath it. Sometimes I wonder if it will ever work. There seems to be a lot of natural language recognition work yet to be done.

    However, if the engine ever does work, it will know quite a lot. Even if most of it is about pr0n.

    --
  • When are we gonna make a computer program that can take the SAT's?

    And of course, the follow-up question: When will that program be ported to my College-Board approved TI-85? :)
  • Philip K. Dick said "Reality is that which, when you stop believing in it, doesn't go away." One measure of sanity is whether your conception of reality agrees with the actual reality.

    But what is that actual reality? Knowing that you're subject to illusions and delusions, how do you verify that your observations correspond to external objective reality? (If such a thing even exists, but that's a whole other topic...)

    Humans are so good at being delusional that Dick's test is useless - when we stop believing in it, we often just stop seeing it! And vice-versa - when we believe in it, we see it whether it's there or not. Our political and social structures are rife with examples of this. (And let's not even start on religion...)

    Tom Swiss | the infamous tms | http://www.infamous.net/

  • Several threads have already recycled the myth that you "can't fool" the MMPI because it repeats questions and checks your answers for consistency.
    Somewhat off-topic, but amusing: when Timothy Leary was jailed for cannabis possession, as part of standard procedure the prison shrink gave him a personality test, so they could see whether he'd be a difficult prisoner. Leary had helped develop this test during his Harvard days, and so gave all the right answers to appear a model prisoner.

    Tom Swiss | the infamous tms | http://www.infamous.net/

  • GAC is a failing AI effort which serves no purpose except for Chris McKinstry to draw attention to himself.

    The site began by offering users shares of the "Corpus" worth approximately 25 cents per question you submitted. Eventually, the running total of the "money" you had earned disappeared. Chris claimed that the software that generated that page was broken, but it has never come back. There was also a "referral program" along the lines of alladvantage, where you could get partial credit for the "Mindpixels" submitted by people you referred. That quietly went away. Asking Chris where the "money" went gets you ignored, and the fact is he didn't really promise money, just shares in whatever money this "Corpus" eventually makes. I suppose he pulled out at a good time, when he realized the total would be somewhere around $0.

    He promised a rating system to get rid of the dumb or repetitive questions and reward the good ones - this never appeared.

    A while later, he got the idea that he could create HAL with the same deficient software that ran GAC, just by telling users to answer questions as they thought the computer HAL would answer. Most people saw that this made no sense whatsoever. The massive funding Chris was expecting for HAL never appeared, and he wrote a bitter news item about it.

    So now he's managed to get GAC signed up for this Turing-Test-ish-thing. GAC still appears to answer randomly on the simplest true/false questions, so I doubt it will do spectacularly. It's just another way to draw attention to Chris.
    --
  • Several threads have already recycled the myth that you "can't fool" the MMPI because it repeats questions and checks your answers for consistency. According to an NPR interview I heard several years ago with the people who designed the MMPI, however, this simply isn't true.

    It _is_ true that the MMPI repeats questions (at least it used to be true; I assume it still does), but the explanation has nothing to do with something sophisticated like checking to see whether you answer the same questions the same way. Instead, when the original designers of the test first wrote it, they discovered that they didn't have enough questions for the grading machine they were using. Their machines (using punch cards I think) required that a certain number of answers be marked or they would spit out the answer sheet, but the test designers were short a few questions, and didn't have any questions they particularly wanted to add. So they simply interspersed a random handful of questions throughout the test in order to get the grading machine to accept the answer sheets.

    Later on, when the grading equipment improved and no longer required a certain number of questions, they retained the extra questions, because by that time the MMPI had already become a widely-used standard, and there was no reason to change it. But the repeated questions never entered into the grade, and were never checked for consistency. The scientists admitted to NPR that they knew (now, years after the fact) that having the repeat questions made people uncomfortable, but this was no part of the design of the test, and never entered into the grading of the test.

    Still, whenever the MMPI comes up in conversation, someone claims that you "can't fool" the MMPI because it repeats questions and checks for consistency.
  • Right. The MMPI is actually a ridiculous test to give to any AI system at this point. Have you ever READ the MMPI? I'd link to a copy online, but it's carefully guarded intellectual property, and costs hundreds of dollars to administer and score. But here's [ncs.com] the NCS page with a Q&A about it if you want some particulars.

    That said, it's fucked up. One of my roommates had to take it once (aside: we moved him out the next semester:), and he let us read it. There are 567 "yes/no" questions, and the first one is "I enjoy reading sports car magazines." Others include such obviously gender biased items as "I sometimes wear women's clothing." Basically, my point is, it's a very US-centric test designed to "catch" people who think differently than our definition of "normal." I suspect that the AI device wouldn't even have a coherent answer to many of the questions, since it's never lived in American culture, and doesn't have a childhood to be analysed as "traumatic," etc etc.

    I can't see anything useful coming from this except perhaps a false reassurance that "this system won't go nuts like HAL-9000."

    ---

  • I think that in a lot of these tests single questions as such have no meaning whatsoever but rather full answer patterns are the thing to look for. Also a lot of times they repeat the same question several times with a little different wording. Inconsistency probably scores low..

    Once a test has been administered several years and answers of several thousand people have been recorded with the actual information about how these people are outside the test (based on observation or known facts) you can start matching new answer patterns with old ones.

    An alarm should go off if your pattern is very similiar to a known rapist/murderer.

  • Interesting you mention Dick. I just reread Martian Timeslip and, while I enjoyed it as much as I did as a kid, I was struck by his facile conception of schizophrenia. At any rate, a quote from Dick on questions of sanity, madness and reality sheds heat but no light. Dick begs the question of the relationship of reality to normative constructs, as well as the reliability and purity of our observation. In MT, the only sane view, that is corresponding to actual reality, is finally that of the two madmen, the kid and the protagonist.

    Certainly, in a society of delusional types, a realist should not be considered mad. Although they almost certainly will be.

    The tyranny of the normative is only just as dangerous as that of absolutes. I can make no apology for fools mistaking the two. Such dangers are the cost of doing cultural business. The realist's response is not to dismiss normative judgements out of hand, but to modify the norm. Such a view also cannot preclude other voices without damage to itself, even as their otherness can only be established with reference to that view.
  • self-fulfilling prophecies are hard to escape. if someone labels you as having the symptoms of 'syndrome XYZ', more than likely you'll end up with syndrome XYZ.
  • I'm wondering how GAC will score on the gender section of the MMPI. I hope they got a good cross-section on their data enterers/validators... I know I've had CS courses before where I was the only woman there.

    -= rei =-
  • Laf!
    I got this question on Mindpixel:

    "I have often wished I were a girl. (Or if you are a girl) I have never been sorry that I am a girl."

    That's an MMPI question! Hehee, methinks GAK is studying up.... ;)

    -= rei =-

  • I think it's much, much closer than most people expect...

    What we're actially doing with GAC is high dimensional tomography. At the moment we're just mapping the 'truth' of each of these high-d points, but soon, we will also measure the 'emotionality' of each point as well. This involves getting people to tell the system how each particular item makes them feel by selecting emotive words from some drop down lists - much like the way 'Quality' is measured now.

    See my Slashdot interview for some more links on this emotional thread.

  • But we've had a program to give psychological tests for I dunno how long now. Isn't this a step backwards?

    Eliza: Can you elaborate on that?

  • I can see it now..

    "We don't know who struck first. But we do know that it was us who scorched the skies."

    I'll only be freaked out when they actually build an AI computer and it happens to be solar powered.

  • Figures.. what lame sods run this site? Well I found some info..

    halfway down the page - Some stuff [time.com]about this 'GAC'

    And something about the test [ncs.com] itself.

  • T/F: Rob Malda goes by the name CmdrTaco on the Internet

    Does this mean that the first artificial consciense will be a /. fan? ;)

  • The article says:
    The test is known as the MMPI-2 (Minnesota Multiphasic Personality Inventory).Developed as a specialized psychological test for the measurement of psychopathology
    I guess it's good to first establish that your computer is not a psychopath...

    What does it say about the designers of the personality, that they feel they first nered to insure they havn't created a psychopath...?

    --CTH


    --
  • Actually, the somatic symptoms are in line with research on depression, which suggests depression is manifested somatically in many cultures.

    Very interesting if what you say is true, and GAC is reflecting these profiles.

    A lot has been made of AI; this brings up the whole issue of AE (artificial emotion). If an AI is able to exhibit typical emotional profiles based on typical associative/NN models, it suggests AE might not be as far off as some thought.
  • Your score: somewhat deviant, highly paranoid with delusions of grandeur. However, since this is Slashdot, you're no different from the rest of us.
  • when you get repaired, they implant water storage units just below the eyes, so that in case you enter an infinitely recursive 'drek' loop, your program will at least let your user know what's going on.

  • Now, a kewpie doll to anyone who can tell us the difference between a disorder and a syndrome. And a boot to the head to anyone who actually cares :)

  • @ Mindpixel, this link. [mindpixel.com] You can also "talk" to GAC via this site.
  • GAC says: Visit our sponsors or donate $2.

    --
  • On the "Talk to GAC" page I asked a question and got this response...

    I think the answer to: Computers, such as GAC, will someday conquer the world and enslave the human race. is:

    TRUE

  • The test won't, however, say that you are a serial killer or homicidal maniac...
    That's ok, everyone already knows that a thinking computer is going to start a war against all humans, slaughtering millions and using their skin to clothe humanoid robots to hunt down the remnants of our species like vermin.

    Either that or they're all robin williams [imdb.com] and haley joel osment [imdb.com]

  • This broken link is clearly a covert attempt by the gubmint and eevil corporations and space mutants and reverse vampires to censor our Most Righteous geekly speech!

    Help, help! We're being repressed!

    --

  • Another problem with having computers calculated to fit their users' personalities would be that it would cause people to separate themselves from society. I'd lock myself in my office and spend hours in conversation with my computer, until my brain is mush and my once-picture-perfect physique resembles a cheese puff. Not that I don't spend hours locked in my office in conversation anyway, but it consists of: "****! Crashed again, you stupid excuse for a toaster oven!" Not exactly scintillating dialogue.
  • IAAP (I am a Psychologist). Here's the deal with the MMPI.

    One of the neat things about the MMPI is that it has low face validity. This means, essentially, that it is difficult to determine what any particular question is getting at. The advantage to this is that it is hard to "beat" the test by giving answers that will result in an uncorrect assessment. There are a number of questions designed to check to see if you are trying to appear crazy or too normal. In addition, there are a number of subscales that are combined to provide a psychological profile of the test taker.

    Most surprising, however, is the fact that statistical techniques utilizing the MMPI have been shown to be MORE effective than trained clinicians at diagnosing psychological disorders.[1]

    Of course, none of this says anything about GAC taking the MMPI.

    • First off, the "article" is a lame PR ploy (go back and read the description of the MMPI administrator, they make him out to be some Nobel-worthy genius).
    • Second, GAC was designed by having individuals provide facts, not by providing judgments or preferences, therefore this exercise will be a test in the relative overlap of mismatching domains.
    • Third any pattern of responses to the MMPI will lead to some result. Most likely it will be barely interpretable, but not particularly deviant in any sense (since GAC input is moderated by lots of people)
    • Finally, we've seen this before. Remember This interview [slashdot.org] or This Announcement [slashdot.org]

    [1] Meehl, P. E. (1959) A comparison of clinicians with five statistical methods of identifying psychotic MMPI profiles. _Journal of Counseling Psychology,6_, 102-109.

    --

  • The acronym (Score:3)

    by hugg ( 22953 ) on Monday July 02, 2001 @09:33AM (#113436)
    G)enerator of A)rrogant C)laims.
  • here's the article.


    For the first time, a standard psychological test used by clinicians worldwide in the evaluation and treatment of adults will be administered to a machine-based artificial personality.

    The test is known as the MMPI-2 (Minnesota Multiphasic Personality Inventory).Developed as a specialized psychological test for the measurement of psychopathology, the MMPI has been the preferred psychosocial diagnostic instrument among clinicians for the past 50 years.

    Originally published in 1940 by Hathaway and McKinley, MMPI has been implemented in many clinical and non-clinical contexts, including medical, educational, medicolegal and organizational settings. A restandardisation and partial revision of the MMPI resulted in the publication of the MMPI-2 in 1989.

    GAC (Generic Artificial Consciousness -- pronounced "Jack") is the artificial personality being developed at the Mindpixel Digital Mind Modeling Project with the collaboration of nearly 40,000 Internet users from more than 200 countries worldwide.

    GAC will be evaluated using the MMPI-2 over the next several months to assess its learning of human consensus experience from the Mindpixel project's large and diverse group of users from many different cultures.

    The test will be supervised and interpreted by Dr. Robert Epstein, one of the world's leading experts on human and machine behavior.

    "Nothing like this has ever been attempted," said Epstein. "We're evaluating thousands of people worldwide as if they were one collective individual."

    "We don't know if it is possible to build a normal personality out of millions of little pieces. This experiment will tell us how reasonable the idea is," Epstein added.

    In the nearly one year the project has been online, Mindpixel's Internet contributors have made nearly 8 million individual measurements of more than 355,000 individual items of human consensus experience.

    The project's organizers hope that they will gain enough information by the time the project's data collection phase is complete (2010) to build a highly accurate statistical model of an average human mind which they hope can be used as a foundation for true artificial consciousness.

    One of the world's leading experts on human and machine behavior, Robert Epstein received his doctorate in psychology at Harvard University in 1981. He is Editor-in-Chief of Psychology Today magazine and University Research Professor at United States International University in San Diego.

    He is also the founder and Director Emeritus of the Cambridge Center for Behavioral Studies in Massachusetts and Adjunct Professor of Psychology at San Diego State University. He was also the former director of the famed Loebner Prize competition in Artificial Intelligence.

    The Mindpixel Digital Mind Modeling Project [mindpixel.com] was launched on July 6, 2000. It is the world's largest Artificial Intelligence effort, with nearly 40,000 contributing members in more than 200 countries.

    [Contact: Dr. Robert Epstein [mailto], Christopher McKinstry [mailto]]

    02-Jul-2001



    use LaTeX? want an online reference manager that

  • Re:MMPI (Score:3)

    by prizog ( 42097 ) <novalis-slashdotNO@SPAMnovalis.org> on Monday July 02, 2001 @10:48AM (#113438) Homepage
    rodentia [hey, wasn't she spammer?] writes:
    "Finally judgements about normativity, while they strike some as distasteful, are really the only way to generalize about psychological phenomena."

    Certainly not. Philip K. Dick said "Reality is that which, when you stop believing in it, doesn't go away." One measure of sanity is whether your conception of reality agrees with the actual reality. Certainly, in a society of delusional types, a realist should not be considered mad.

    r:
    "The idea of universal sanity or a generalized idea of madness are simply absurd and possibly dangerous."

    Certainly, they are not as dangerous as a culturally influenced definition of same. Just ask a gay person.

  • MMPI (Score:3)

    by hodeleri ( 89647 ) <drbrain@segment7.net> on Monday July 02, 2001 @09:29AM (#113439) Homepage Journal

    The MMPI is quite comprehensive. It is designed so that it is effectively impossible to hide anything. My psych professor said that he took one and (knowing how the test was designed) he tried to cover up that he had a major traumatic event in his life (which he did). The test showed it anyhow.

    The test won't, however, say that you are a serial killer or homicidal maniac...

  • IRTP: I run this project.

    You are right, GAC is one heck of a psychological test on its own. However, unlike the MMPI, GAC has not explicitly been tested with both normal and clinical populations, so it would not be good at distinguishing the two.

    The whole point of giving the MMPI to GAC now is to see what type of personality you get when you blend together 40,000 personalities. Looking at the data as it comes in (after recovering from the slashdot hit that killed the site for a while), GAC looks a little depressed and slightly sexually deviant. GAC also is showing some strong somatic symptoms (complaints about the body) which is of course quite ironic considering it doesn't have a body. But other than that, GAC appears normal. Quite human.

  • And the winner is:

    1. Question asked of GAC 07/01/2001 16:03
    2. Registered Login Required [href] [mindpixel.com]
      --------
      I think the answer to: Donating $2.00 via PayPal is a good way to contribute to the mindpixel project is:

      FALSE



    ---

  • And the purpose of this is what...? (Score:3)

    by kriemar ( 247929 ) on Monday July 02, 2001 @10:06AM (#113442)
    The site is slashdotted, so it's difficult to determine what exactly is going on.

    About the beauty of the MMPI: the MMPI is empirically validated, meaning that its scales were developed by selecting items that correlate with an objective criterion. Because items might correlate with an objective criterion (e.g., homicide) without looking like they would, you can get "subtle" scales--scales that are difficult to fake responses to.

    But what's the point of giving GAC this?

    Say the test predicts the computer is a psychopathic deviate. Does this mean the GAC is not functioning like a normal individual? Does it mean the GAC is psychopathic? Does it mean the average internet user who supplied observations is a psychopathic deviate?

    What's ironic is that GAC may actually be a more comprehensive psychological resource than the MMPI. By selecting observations from so many individuals, GAC has tremendous data on what typical thought patterns are.

    In fact, GAC could be used as a psychological test itself. This may be why they are giving GAC the MMPI. If GAC is "normal", so to speak, you could use GAC as a test. Even if it's not normal, you could "adjust" GAC to have responses more in line with a "normal" MMPI profile.

    Then, you could "test" individuals by having them converse with GAC. The extent to which you "agree" with GAC or not is a gauge of the deviance of your personality. Ideally, it would be just like having a conversation with someone, only the extent to which you get along with GAC reflects on your abnormality.

    Interesting...
  • "Dr. Sbaitso" _WAS_ Eliza. Same algortihm and everything...only named differently so as not to pay any royalties to the copy of "101 BASIC Computer Games" they lifted it from. They stuck in a stupid age check if you tried to talk to the doc about sex...which sucks, because I've a feeling that if my Thunderboard could have helped me through my youthful urges, I wouldn't be the cross dressing deviant I am today.

  • What is the Mindpixel Corpus? (Score:4)

    by Neon Spiral Injector ( 21234 ) on Monday July 02, 2001 @09:38AM (#113444)
    From Mindpixel's website:

    The Mindpixel Corpus is the world's first and largest database of validated consensus human knowledge. It is an ever improving approximation of the mind of an average Internet user, constructed and owned tens of thousands of people just like you from all over the world, speaking all of the world's languages.


    Emphesis added by me.

    So, this thing is going to be obsessed with eBay and pr0n.

    --

  • Democratic intelligence (Score:4)

    by Shotgun ( 30919 ) on Monday July 02, 2001 @09:59AM (#113445)
    "We don't know if it is possible to build a normal personality out of millions of little pieces. This experiment will tell us how reasonable the idea is," Epstein added.

    I predict that the result will be about as useful as Congress.

  • advertizing (Score:4)

    by Refrag ( 145266 ) on Monday July 02, 2001 @09:30AM (#113446) Homepage
    You've gotta love this stealth advertizing for Spielberg's AI!


    Refrag
  • Didn't we try this 30 years ago? Did it work then?


    --

  • Re:Hello. My name is Eliza. What's your problem? (Score:5)

    by Anonymous Coward on Monday July 02, 2001 @09:41AM (#113448)
    Why do you think it didn't work then? Tell me about your 30 years ago.

  • Re:MMPI (Score:5)

    by rkent ( 73434 ) <rkent AT post DOT harvard DOT edu> on Monday July 02, 2001 @09:51AM (#113449)
    And for this reason, the MMPI is actually a ridiculous test to give to any AI system at this point. Have you ever READ the MMPI? I'd link to a copy online, but it's carefully guarded intellectual property, and costs hundreds of dollars to administer and score. But here's [ncs.com] the NCS page with a Q&A about it if you want some particulars.

    That said, it's fucked up. One of my roommates had to take it once (aside: we moved him out the next semester:), and he let us read it. There are 567 "yes/no" questions, and the first one is "I enjoy reading sports car magazines." Others include such obviously gender biased items as "I sometimes wear women's clothing." Basically, my point is, it's a very US-centric test designed to "catch" people who think differently than our definition of "normal." I suspect that the AI device wouldn't even have a coherent answer to many of the questions, since it's never lived in American culture, and doesn't have a childhood to be analysed as "traumatic," etc etc.

    I can't see anything useful coming from this except perhaps a false reassurance that "this system won't go nuts like HAL-9000."

    (yes, this is posted under another message below, but it fits better here.)

    ---

  • Re:MMPI (Score:5)

    by rodentia ( 102779 ) on Monday July 02, 2001 @10:14AM (#113450)
    I agree that giving this test to an AI system is totally marketroid hype. I'd like to clarify your view of the MMPI, having taken it twice.

    Yes, some of the questions do seem a bit bizarre and it is often difficult to concieve either the purpose of the question or how to answer, but there is tremendous redundancy built into the test and it is scored on a curve. That is, answering yes to question 241 does not tag you a psychopath; ultimately the results are correlated against the sampling of individuals who have taken the test, as is the Rorshach. The tested individual is found to have tested within some standard deviation along nine (IIRC) scales. Individuals with particular patterns of results can be associated with others with similar patterns. Occasional questions are "hot buttons" designed to illicit responses which indicate that the subject has poor reality checking or exhibits dangerous behavior. Of course, the test is only useful in conjuction with clinical, therapeutic observation.

    Finally judgements about normativity, while they strike some as distasteful, are really the only way to generalize about psychological phenomena. The range of normative behavior, while flexible, is the only standard available. The idea of universal sanity or a generalized idea of madness are simply absurd and possibly dangerous.

  • That broken link (Score:5)

    by General_Corto ( 152906 ) on Monday July 02, 2001 @09:27AM (#113451)
    Is fixed here. [unisci.com]

Slashdot Top Deals

Top Ten Things Overheard At The ANSI C Draft Committee Meetings: (7) Well, it's an excellent idea, but it would make the compilers too hard to write.

Close