Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

The Profoundly Weird, Gender-Specific Roots of the Turing Test

Soulskill posted about 4 months ago | from the i'm-sorry-dave,-these-shoes-are-half-off dept.

AI 136

malachiorion writes: Alan Turing never wrote about the Turing Test, that legendary measure of machine intelligence that researchers claimed to have passed last weekend. He proposed something much stranger — a contest between men and machines, to see who was better at pretending to be a woman. The details of the Imitation Game aren't secret, or even hard to find, and yet no one seems to reference it. This article explains why they should — in part because it's so odd, but also because it might be a better test for 'machines that think' than the chatbot-infested, seemingly useless Turing Test.

cancel ×

136 comments

Sorry! There are no comments related to the filter you selected.

Wow (3, Informative)

Anon-Admin (443764) | about 4 months ago | (#47231343)

That would be a hard test. Most guys can not even pull it off. Lord knows I have seen a lot of guys online trying to pretend to be women who just can not even get the basics down.

Re:Wow (4, Funny)

Tablizer (95088) | about 4 months ago | (#47231391)

Some vending machines have the best impressions of women: take your money for nothing in return and then pretend like nothing happened ;-)

I Think That Alan Turing Himself (0, Flamebait)

Jeremiah Cornelius (137) | about 4 months ago | (#47231607)

May have been an expert at pretending to be a woman.

Of course, not in the league of J. Edgar Hoover...

Re:I Think That Alan Turing Himself (2)

Jeremy Erwin (2054) | about 4 months ago | (#47231927)

Real men (such as Turing) prefer the company of other men.

Re:I Think That Alan Turing Himself (1)

GameboyRMH (1153867) | about 4 months ago | (#47232179)

Not sure if joking about Turing's homosexuality or unaware of it...

(fry_notsure.jpg)

Re:I Think That Alan Turing Himself (1)

gstoddart (321705) | about 4 months ago | (#47232221)

Dude ... I don't play for Turing's team, and even I can tell you .... WHOOOOSH!!

Re:I Think That Alan Turing Himself (0)

Anonymous Coward | about 4 months ago | (#47233035)

Company yes, intercourse no. Real men prefer intercourse with real women.

Re: Wow (0)

Anonymous Coward | about 4 months ago | (#47231871)

+3
Concise and clear specifications for V&V testing

Re:Wow (1)

gstoddart (321705) | about 4 months ago | (#47231489)

Yeah, but short of an explicit sex chat ... I'm not even sure how you go about this.

"Are you a woman?" "Yes"
"Do you have b00b13s?" "Yes"

I'm pretty sure my wife would fail any questions regarding makeup or cosmetics.

I've known more than a few women who could swear like sailors ... maybe they were actually sailors.

I'm apparently suffering from a huge imagination fail, because I have no idea how one would do this in a text chat.

Re:Wow (5, Funny)

gnick (1211984) | about 4 months ago | (#47231639)

I have one wife, one ex-wife, one mother, one step-mother, one sister, one step-daughter, and more non-immediate female relationships/acquaintances than I care to enumerate. ANYONE could fake a woman in a chat with me, because from experience, I have no idea what to expect.

Re:Wow (3, Insightful)

gstoddart (321705) | about 4 months ago | (#47231705)

Wow, neither my mother nor my wife are the crazy irrational beasts that I keep hearing about. As far as I can tell, my sister in law and my cousins, also not crazy irrational people. Most of my exes, also not crazy irrational.

OK, I had a girlfriend in highschool who was.

Either I've been lucky, or women aren't these un-knowable entities everyone keeps claiming.

Though, my brother did date his share of crazies, and an uncle's ex-wife was definitely crazy ... but in a general crazy sense, not so much with the "crazy because she's female" sense.

Then again, I'm hardly famous for my insights into individual people. :-P

Re:Wow (3, Insightful)

Captain Splendid (673276) | about 4 months ago | (#47232005)

You're not lucky, you just have a broader range of human experience.

The sad truth is, all us humans are a little crazy (aka human). It's just only seen as a bad thing if you have a vagina.

Re:Wow (1)

gstoddart (321705) | about 4 months ago | (#47232103)

You're not lucky, you just have a broader range of human experience.

LOL ... that or I'm so universally terrible at human nuance I've never picked up on gender differences.

Tough call. ;-)

The sad truth is, all us humans are a little crazy (aka human).

I take that as axiomatic.

Re:Wow (-1, Troll)

epyT-R (613989) | about 4 months ago | (#47232397)

No, these days it's seen as a bad thing if you have a penis and it is expected that we celebrate those who have vaginas, no matter how mundane the accomplishment (if there's any at all).

Re:Wow (0)

Anonymous Coward | about 4 months ago | (#47232037)

Just think of a man, and then remove reason and accountability.

Re:Wow (2, Interesting)

Anonymous Coward | about 4 months ago | (#47231685)

There's a lot more to it. Women use different colloquialisms than men do.

I was at a conference a few months back where one of the keynote speakers was a MTF. If I closed my eyes, and just went on words I would have never have known they were MTF as they sounded completely male from the tones and phrases used - the colloquialisms of being male, and that's a hard thing to relearn.

This is how it's done (0)

Anonymous Coward | about 4 months ago | (#47231833)

Rachael: The egg hatched...

Deckard: Yeah...

Rachael: ...and a hundred baby spiders came out... and they ate her.

Re:Wow (2)

Jeremy Erwin (2054) | about 4 months ago | (#47231903)

Actually, some men are fairly practice as pretending to be women in the context of (online) sex, but probably are less familiar with pretending to be women in other contexts.

I put on my robe and wizard hat.

Re:Wow (2)

lgw (121541) | about 4 months ago | (#47232059)

Remember that turning worked during the war with the 40s equivalent of geek girls - intelligent, driven, not shrinking violets. He wasn't talking about that shallow crap. He was talking about the fact that in the 40s even geek girls had a quite different perspective than men.

So, the bot needed to not only pass as human, but have a sufficiently deep understanding of the human condition to know what different sorts of answers to everyday questions a man and a woman would give, without simply being a 40s stereotype.

But I disagree - I don't think an understanding of the human condition specifically is in any way needed for sapience or self awareness, but an broader sort of awareness as one member of society. What's needed (if we discard the supernatural) is the ability to model the world (including the social aspects) abstractly and make decisions based on mentally evolving that model to see the likely outcomes of choices - as opposed to following a set of rules.

Re:Wow (0)

Anonymous Coward | about 4 months ago | (#47231771)

So what exactly are the "basics" of pretending to be a woman? Because I'm curious how many women would fail based on those basics.

Re:Wow (2)

Anon-Admin (443764) | about 4 months ago | (#47231963)

Being able to answer simple questions, ones that every girl learns by age 13.

Things like references to there 28 day cycle. I have commented that someone must be in the first 7 days of 28 and had the person in chat ask what I meant. When I replied "You know, your 28 day cycle?" I have been asked "What? I dont understand. 28 days of what?"

Most guys when asked their favorite color of lipstick reply with RED. Hint, there is no red. There is "Wild Orchid" and "Ruby" but no lipstick is just RED

You can also ask about pantyhose sizes, panty sizes, dress sizes, Hair colors, etc, etc. Lots of things that guys pay no attention to.

Then you get to the more obscure stuff like sex during a period tends to relieve cramps, Women will eat something before a first dinner date because the date is about the conversation and not the food. Heck if she gets into Sexting you can really toss some fun stuff in like descriptions of what you are doing to her labia or how you are pressing her cervix. Then watch to see how they reply, do they even know where those parts are?

The joy of growing up with 2 sisters, having two daughters, a wife, and a girlfriend. You learn a lot about women. lol

Re:Wow (2)

gstoddart (321705) | about 4 months ago | (#47232033)

furiously scribbles down notes

Re:Wow (0)

Anonymous Coward | about 4 months ago | (#47232155)

Heat applied to the abdomen over the ovaries will relieve or remove even the worst menstrual cramps. Heat wet towel in microwave until very hot, wrap in thinner towel/cloth, position over ovaries (put on, remove when too hot, repeat). Iterate with more heated towels for the 10 - 20 minutes required for the heat to work into the ovaries. Then accept her thanks.

Why more women don't know this is beyond me.

Re:Wow (0)

Anonymous Coward | about 4 months ago | (#47232489)

Not only that, you end up becoming one yourself.

Re:Wow (3, Interesting)

Charliemopps (1157495) | about 4 months ago | (#47231789)

That would be a hard test. Most guys can not even pull it off. Lord knows I have seen a lot of guys online trying to pretend to be women who just can not even get the basics down.

I disagree. I used to be pretty heavy into MMOs prior to WOW ruining everything. I was one of the few that didn't have a problem having a female character... and I got hit on CONSTANTLY. Seriously, my female characters would randomly receive gifts via mail or in person and I wasn't even remotely trying to pretend I was female. MMO dudes are just that desperate, they dont care to check if you're really female or, even if you are, if you're actually attractive in real life. And we're not talking about healing potions... we're talking stuff that cost hundreds of real world dollars. It was so funny it became a running joke in my guild who started passing around pictures of both models and ugly women to entice, shame or even enrage my "suitors" I'd even put 'NOT A CHIC' in my profile but to no avail. It really opened my eyes to just how desperate some people are.

Nowadays it doesn't seem as bad. I think there are either more women into MMOs...

Re:Wow (1)

Joe Gillian (3683399) | about 4 months ago | (#47232171)

I think a lot of that can be attributed to WoW and the advent of mandatory or near-mandatory voicechat to do group content. I can still fondly remember my days of raiding Karazhan in Burning Crusade and having the guild leader complain loudly at the people who moved during Shade of Aran's fire rings. You were required to have Ventrilo or TeamSpeak, and use them constantly. Most modern games use some form of voicechat, and a large subset of those have lazy programmers who use always-on voicechat with no push to talk. That's probably cleared up a good percentage of the people who were actively attempting to imitate females.

Re:Wow (0)

Anonymous Coward | about 4 months ago | (#47232181)

>Dudes are just that desperate

FTFY

Re:Wow (1)

Anonymous Coward | about 4 months ago | (#47231851)

I dunno. Most guys just fall for it, in my experience.
~ Alice

Re:Wow (1)

Boronx (228853) | about 4 months ago | (#47233155)

Let's face it. If you're a guy chatting with a woman, you don't want to find out she's really a dude.

Re:Wow (2)

Jeremy Erwin (2054) | about 4 months ago | (#47231873)

Re:Wow (1)

TangoMargarine (1617195) | about 4 months ago | (#47232891)

Yeah, because I'm going to plug their chat into a chi-square language analyzer. Simple this surely ain't.

Re:Wow (1)

tokizr (1984172) | about 4 months ago | (#47232163)

I would imagine his intent was not that the machine would achieve success, the experiment is simply a nice framework to analyse weather the machine is able to comprehend information. Weather the machine is convincing or not, if the machine can abstract concepts in the same we do then you'd have a thinking machine. The pretending scenario seems just like a simple way to make it harder for someone to make a cheap solution to the problem (i.e. a chatbot).

Ultimately producing real intelligence is what is sought, not passing the damned test.

Re:Wow (2)

sir-gold (949031) | about 4 months ago | (#47232317)

A recent study of World of Warcraft players showed that male players who played as female avatars had a subconscious tendency to adopt female speaking characteristics.

http://www.slate.com/blogs/fut... [slate.com]

"When selecting female avatars, these men strongly preferred attractive avatars with traditional hairstyles—long, flowing locks as opposed to a pink mohawk. And their chat patterns shifted partway toward how the real women spoke: These men used more emotional phrases and more exclamation points than the men who did not gender-switch. In other words, these men created female avatars that were stereotypically beautiful and emotional."

Re:Wow (1)

Krishnoid (984597) | about 4 months ago | (#47232569)

You want difficult? In the spirit of another recent story [slashdot.org] , see if you or your software can both convincingly imitate a pregnant scientist as well as get the dean to give you tenure.

Curse of AI (1)

Anonymous Coward | about 4 months ago | (#47231345)

Isn't this just another case of "The AI curse". As soon as a goal is reached, everyone declare that it wasn't "real AI after all", moving the goal post post-facto.

Re:Curse of AI (0)

Anonymous Coward | about 4 months ago | (#47231471)

No, it's not. That recent alleged 30% pass of the Turing was just so much media puffery.

Re:Curse of AI (2)

mark-t (151149) | about 4 months ago | (#47232223)

That, and it wasn't even that hard to spot as an AI. I recall having a go at the chatbot in question back in 2012, and found it as crtically flawed after asking it just two questions. First, I asked how old he was, and he responded with a believable answer of 13, which corresponded with information that I already had, but then I asked when his birthday was and he responded with, if I remember correctly, a date in January of 1988, which would have made him 11 years older than what he was otherwise claiming. The straightforwardness of the questions and their answers left no doubt in my mind that the discrepancy was not merely on account of any so-called lack of fluency in English (which was, by the way, the excuse that it would appear to fall back upon when it was not able to from a coherent response), and the bot was exposed. A non-native speaker who genuinely did not understand a question in the language it was posed in would, in fact, just say that they did not understand the question, rather than give a coherent answer that blatantly contradicts a previous coherent answer they had already given to a differently worded but highly related question.

The notion that at least 30% of the researchers would not even think to ask an alleged child when their birthday was is laughable.

Re:Curse of AI (5, Insightful)

Lab Rat Jason (2495638) | about 4 months ago | (#47231581)

It's more like a case of people pushing the goal posts back to where they originally were, after some over zealous AI zealot moved them forward to make his failure look like a success...

Re:Curse of AI (0)

Anonymous Coward | about 4 months ago | (#47232003)

The test was famous, not good. If you run enough samples of 10 people, you can find 3 idiots with high probability, particularly if they think the computer is trying to fake being a foreign child, rather than an average person one might converse with.

Re:Curse of AI (0)

Anonymous Coward | about 4 months ago | (#47233031)

The test was famous, not good.

The original paper doesn't give many details, however it describes the "game" as a chat between a human, a machine and an interrogator trying to find out which is which. There is no time limit, there is no the human may be a retarded or unable to speak the language and certainly there is no the interrogator may be some random hoodlum taken from the street.

The organizers and winners of that test combined the worst possible interpretation by

a) minimizing the time an interrogator had for each chat,

b) not requiring the interrogator to be even remotely aware of computer science

c) allowing bots that "don't speak the local language" and pretend to be small children

d) being under the lead of Professor Cyborg - a person known for his overly optimistic predictions about working terminator like cyborgs within the next decade.

The points a-c made it harder for the interrogators to judge if they where talking to a human or not since they had little time and most likely no idea how to make the over hyped chat bot fail. The test may have been set up this way to prove d) right.

However the chat bot itself got criticized by quite a few people and some of it shows that you may be at least partly right with the 3 idiots out of 10 people. The bot pretended to barely understand English to cover its random stock responses, however each response by itself was in near perfect english, no grammar problems, no misused or misspelled words.

Re:Curse of AI (1)

ctheme (2694307) | about 4 months ago | (#47233041)

If you run multiple trials of 10 participants and wait until you get a 30% failure rate on AI identification, you don't simply discard all of the previous data which was collected. It is still included in the figure you achieved when you finally "passed" the test.

Re:Curse of AI (1)

gstoddart (321705) | about 4 months ago | (#47231619)

Isn't this just another case of "The AI curse". As soon as a goal is reached

I'm sorry, but nothing about that charade where someone claimed to pass the Turing test implies that a "goal was reached".

Except the people who claim it, nobody actually believes it.

Re:Curse of AI (3, Insightful)

fuzzyfuzzyfungus (1223518) | about 4 months ago | (#47231665)

Arguably, the 'AI curse' is only partly goalpost-moving by humans obsessed with their special uniqueness.

The other aspect of it (as well a genuinely interesting result of whatever attempt at AI was made) is the discovery that we actually handle much less of what we do in some sort of naive, idealized, "high-level, general-purpose, cognition" than we naively suspect, and rather more in specialized and unconscious mechanisms(this lesson can be learned from the other direction as well: something like face blindness, in otherwise cognitively and visually normal people, simply wouldn't be possible if object recognition were a general-purpose function handled by an 'intelligence' with access to a video stream...) And, even when we aren't crunching stuff unconsciously on quite special-purpose mechanisms, we are sometimes just dumb. Good old Youtube comments would probably allow a babbling Markov chain to pass a Turing test.

There's also the fact that humans are frequently easier to fool than they would like: It's not exactly news that people will see faces on the moon, a known sterile rock, impute emotions (and sometimes entire spirits or deities) to the weather, emotionally bond with tamagotchis and similar nonsense.

Yes, people are likely to dismiss every AI that doesn't end up murdering them all and rendering them for computronium as 'just an expert system'; but it's also arguably the case that using a Turing test to check for AI substantially rests on the assumption, more or less Cartesian and more or less nonsense, that man is first and foremost an abstract 'thinking thing', with some other stuff tacked on that philosophers and mathematicians needn't really worry about.

Re:Curse of AI (1)

Immerman (2627577) | about 4 months ago | (#47232041)

>Good old Youtube comments would probably allow a babbling Markov chain to pass a Turing test.

Come now, don't be rude. You shouldn't disparage the coherence of the average babbling Markov chain like that.

How is that stranger? (3, Insightful)

Immerman (2627577) | about 4 months ago | (#47231359)

You're asking a machine to mimic something profoundly alien to it's nature, to put things on an equal footing the man should have to do so as well.

And please, let's not get in to the similarity/difference argument. Yes, the similarities between the minds of men and women far outweigh the differences, but the differences are still profound.

Re:How is that stranger? (1)

grasshoppa (657393) | about 4 months ago | (#47231623)

How can computers be so alien to us when we've designed them? No, alien isn't quite the right word to use here, but rather lacking in development. You might say they are a proto-intelligence; all we've been doing, for the past 50+ years, is building the foundation for real artificial, rational thought.

You can't label something "alien" simply because you don't recognize it.

Re:How is that stranger? (1)

gstoddart (321705) | about 4 months ago | (#47231795)

How can computers be so alien to us when we've designed them?

And if we ever achieve AI, it will probably be very different from us ... because it will be based on our best approximations of the mechanisms of the brain, and quite unlikely to match exactly how we actually work.

And, really [reference.com] :

noun
1.
a resident born in or belonging to another country who has not acquired citizenship by naturalization (distinguished from citizen ).
2.
a foreigner.
3.
a person who has been estranged or excluded.
4.
a creature from outer space; extraterrestrial.
adjective
5.
residing under a government or in a country other than that of one's birth without having or obtaining the status of citizenship there.
6.
belonging or relating to aliens: alien property.
7.
unlike one's own; strange; not belonging to one: alien speech.
8.
adverse; hostile; opposed (usually followed by to or from ): ideas alien to modern thinking.
9.
extraterrestrial.

Number 7 is about spot on.

Re:How is that stranger? (1)

Immerman (2627577) | about 4 months ago | (#47231955)

No, I think alien is exactly the right word. Consider: computers operate exclusively via rigorous logical procedures - a mechanism that a disciplined human mind can mimic, but is not innately well suited to. Meanwhile the heuristics, intuition, emotional responses, and random chaotic neural activity that dominate human consciousness are almost completely beyond the reach of a computer. The day may well come when we can create artificial minds that can mimic those qualities, but so long as they are created as software running on a digital machine their foundations will be fundamentally different that the chaotic organic circuitry that our own are built upon, and their similarity to us will be limited by how well we understand the mechanisms of our own consciousness - which so far are almost completely opaque to us.

You may as well say that simply because we designed them, the nature of a hammer-drill is not fundamentally alien to the nature of a human being - and yet I have never once bored a hole through something by spinning rapidly while bashing my head against it.

Re:How is that stranger? (0)

Anonymous Coward | about 4 months ago | (#47232277)

>bored a hole through something by spinning rapidly while bashing my head against it.

Apply tequila and repeat the experiment.

Re:How is that stranger? (0)

Anonymous Coward | about 4 months ago | (#47232393)

Complex systems that bugger your comprehension aren't necessarily chaotic. On a protein-synthase level, biological organisms are rigorous logical procedures.

Re:How is that stranger? (1)

Immerman (2627577) | about 4 months ago | (#47232597)

I use chaotic in a mathematical sense - in which case that's *exactly* what it means: Massively complex systems in which minor variations in the starting conditions can result in very different outcomes.

And no - even on a protein synthase level biological organisms are chaotic: each chemical reaction depends on the appropriate molecules randomly colliding with the appropriate cellular mechanism with the proper orientation and kinetic energy for the reaction to be possible, while the whole lot of it is suspended in a churning chemical soup, most of which has nothing to do with the particular function you are observing. The animations where you see the parts coming together in a graceful ballet make the mechanisms far more comprehensible, but are deeply misleading as to the actual nature of the environment. That the mechanisms are as reliable as they are is a testament to the fault-tolerance of our biology, not the logical rigor of the machines. With enough protein synthesis locales it doesn't matter if one takes six weeks to produce a single protein molecule while another makes one in a few minutes. And the proteins designs themselves are tolerant enough that a few misplaced atoms probably won't render it useless, and even if it does there's plenty of other proteins around to take up the slack.

Re:How is that stranger? (4, Insightful)

nyctopterus (717502) | about 4 months ago | (#47231675)

Define "profound". You make it sound like men and women's minds start from completely different places and end up converging on similarity, but that's absurd. Men and women differ statistically over populations, but individuals might fall pretty much anywhere in the spectrums of things that differ. There's no way I would be confident of identifying the gender of an individual in this sort of scenario. Statistically, I'm sure I could do a lot better than chance, but each one is pretty uncertain.

Re:How is that stranger? (4, Interesting)

Immerman (2627577) | about 4 months ago | (#47231863)

Try it the other way around - men and women's minds start from essentially the same foundation, but then diverge thanks to profoundly different optimal reproductive strategies (with all the contingent physical and hormonal differences evolution has thus adopted), cultural indoctrination, and no doubt myriad other minor factors. Certainly the standard deviation is greater than the population difference on many fronts, maybe most, but the distinction is undeniable to anyone closely and honestly involved with numerous members of both genders. Grab any two random individuals of opposite genders and you will almost certainly find certain characteristic differences between them.

Re:How is that stranger? (1)

Chalnoth (1334923) | about 4 months ago | (#47232369)

Nope. Almost all of the difference between men's brains and women's brains appears to be culturally-produced, and has little to nothing to do with, "optimal reproductive strategies." I'm pretty sure that no purported difference in brain structure or behavior between men and women has held up under scrutiny. I'm sure there are some differences that are not dependent upon culture (else we wouldn't have transgender people and everybody would be bisexual), but those differences are so small as to be unmeasurable in practice (so far).

Re:How is that stranger? (1)

Anonymous Coward | about 4 months ago | (#47231875)

Culture helps dictate that most adults will be better at certain tasks depending on their gender. No, I'm not talking about workplace tasks, because those are easy to learn one way or another, I'm talking about the things you typically don't think about, that you simply absorb (and thus you don't put in a conscious effort to choose one way or another):

For example, watch Mythbusters when they had to put on heels to drive a car. It isn't because they wouldn't be able to perform such a task, it's because culturally they'd never worn such footwear and thus had no idea how to walk in it. Men typically sit with their legs apart, women don't due to clothing differences. A difference can be seen in the gait of men and women, likely due to each group watching and learning how others of their gender prefer to walk. There can even be language differences.

Culture has a strong effect on how you carry yourself, and gender differences are still part of culture. Even when women/men are told of the differences and instructed to try doing things the other way, old habits die hard. A perfect switch is not easy.

Re:How is that stranger? (1)

epyT-R (613989) | about 4 months ago | (#47232611)

Gait is largely determined by bone and joint structure, which is quite different for men and women. It is not determined by culture. This attempt by the left to completely separate cultural and biological differences and hold the environment responsible for every difference is childish reasoning at best, and duplicitous at worst. The biology defines different 'startup states' for the sexes, and from there, the environment and individual choice alter things, but the outcomes will more often than not follow similar tracks due to sex. Men gravitate towards certain activities/choices/environments and away from others. Women do the same, with different preferences. The differences between the sexes are not that different in scope than those between two different species of the same family tree. This is ok. It's called diversity.

Re:How is that stranger? (1)

MindStalker (22827) | about 4 months ago | (#47231829)

And that was the test, to see if a computer could mimic a women as often as a man can mimic a women.

The computer has to do as well as a typical man, not as well as a typical women at being a women.

Re:How is that stranger? (1)

Immerman (2627577) | about 4 months ago | (#47231979)

Exactly.

Re:How is that stranger? (1)

radtea (464814) | about 4 months ago | (#47232055)

You're asking a machine to mimic something profoundly alien to it's nature, to put things on an equal footing the man should have to do so as well.

But you're also concluding that if the machine does it as well as the human it is "really" a human intelligence, but if a man does it as well as a woman he is not "really" a man.

The basic premise of the test is, "If two unlike things behave alike in one case, we say they are the same; in the other case, we say they are different."

The premise of the test violates its conclusion.

Re:How is that stranger? (0)

Anonymous Coward | about 4 months ago | (#47232215)

>And please, let's not get in to the similarity/difference argument

What is the difference between a dog and a cat?

Re:How is that stranger? (1)

Immerman (2627577) | about 4 months ago | (#47232305)

One worships you, and the other demands worship?

IRC (2, Funny)

Anonymous Coward | about 4 months ago | (#47231437)

What a minute, isn't this what IRC was invented for? For guys to go in to sex channels and pretend to be women and for IRC bots to pretend to be women too? I though this was already a settled matter...

Re:IRC (1)

operagost (62405) | about 4 months ago | (#47232151)

Indeed. By the way, ASL?

Re:IRC (1)

sir-gold (949031) | about 4 months ago | (#47232359)

IRC would be the perfect test bed for a turing test. The AI only has to be as convincing as a real IRC user, and some of those "real users" would barely pass a normal Turing test.

Read the whole article (0)

hahiss (696716) | about 4 months ago | (#47231479)

Of you read past the first section, you can plainly tell that the imitation game he had in mind is the one widely attributed to him. The sample dialog for the machine case isn't gendered. It talks about poetry, math, and chess.

Re:Read the whole article (1)

Garfong (1815272) | about 4 months ago | (#47232047)

Women don't talk about poetry, math, and chess?

This alternate test sounds really easy:

Q: Add 34957 to 70764.
ELIZA: Don't you ever say Hello?
Man: What does this have to do with being a woman?

Re:Read the whole article (1)

Immerman (2627577) | about 4 months ago | (#47232127)

Yes, but especially in Turing's time men and women would typically have rather different perspectives on such things thanks to very different typical roles in society (And how about the scandalous Spanish rebranding of the Vizier in chess to the Queen which took Europe by storm, making the most powerful piece on the board female. Though admittedly that was well before Turing's time). By forcing men to try to bridge that social gap in their conversation he was putting them at a disadvantage not totally unlike the gap between a human mind and one built on a foundation of rigorous logic. At a minimum, at least both contestants were pretending to be something they were not.

worst headline clickbait ever (1)

Noah Haders (3621429) | about 4 months ago | (#47231485)

the headline might as well have been, "one weird trick to designing a turing test"

Re:worst headline clickbait ever (1)

Lab Rat Jason (2495638) | about 4 months ago | (#47231611)

Oh... that made me laugh! I've started developing a mental filter for the phrase "One weird..." because it is used so damn much.

Re:worst headline clickbait ever (0)

Anonymous Coward | about 4 months ago | (#47232065)

Slashdotters hate him!

Re:worst headline clickbait ever (0)

Noah Haders (3621429) | about 4 months ago | (#47232083)

slashdotters hate who?

Not really (0)

Anonymous Coward | about 4 months ago | (#47231577)

The Imitation Game is given with an example of two human participants where a third has to interrogate both and decide which is the real woman, computers aren't mentioned in the example (The paper is linked by wikipedia so it is indeed easy to find). The test involving computers places the computer as pretender against a man (the real human) - so no the computer does not have to pretend to be female, its just given to explain the test.

Also the turing test was not beaten - apparently the guy responsible for it is also known as mister cyborg and even claimed that the "winner" used a super computer (it ran on an underpowered laptop).

We haven't even begun (4, Insightful)

Archtech (159117) | about 4 months ago | (#47231583)

to understand how a machine could be made to pass the Turing test (or the woman test) honestly and thoroughly. To do so, it would have to understand arbitrary human statements and questions: not just "why is the sky blue?" (relatively easy) but "why doesn't my wife understand me?" and "is the real rational, as Hegel posited, and if so (or not) why (not)?" Note that the machine could reasonably pretend to know nothing about Hegel, but it would have to react like a normal human being. No obfuscation such as pretending to be foreign, a child, thoroughly ignorant, or befuddled by drugs should be accepted.

Going a little further, it would have to cope with (very) simple jokes such as "I asked my dog which team would win the World Cup"/"What did he say?"/"Nothing. HE'S A DOG".

some weird thoughts (-1, Flamebait)

iggymanz (596061) | about 4 months ago | (#47231629)

Turing was gay, as such did he have some culturally "feminine" interests or ways of thinking, or was he more a "man-gay"

Re:some weird thoughts (1)

swb (14022) | about 4 months ago | (#47231713)

Maybe the key to the Turing test is one question -- Top or Bottom?

Re:some weird thoughts (1)

iggymanz (596061) | about 4 months ago | (#47231749)

not quite, fooling someone into believing the opposite. Catchers playing pitcher, or bananas to someone's doughnut (japanese phrase there).

Re:some weird thoughts (1)

gstoddart (321705) | about 4 months ago | (#47231867)

So, what about switches? Surely it's not an "all one or the other" trait.

Re:some weird thoughts (1)

iggymanz (596061) | about 4 months ago | (#47232435)

that's merely another possibility for a test, can a switch-hitter fool someone into thinking they're not

Re:some weird thoughts (1)

Etcetera (14711) | about 4 months ago | (#47231845)

Turing was gay, as such did he have some culturally "feminine" interests or ways of thinking, or was he more a "man-gay"

Not so weird. There may be plenty of sociological reasons one could consider for making this gender (or sex) specific that are probably pretty valid. (Men and women have dramatically different ways of understanding communication, and this was not unknown in the 1950s.)

But if the rest of us are forced to consider Turing's homosexuality as a person indivisible from his work as a visionary (OMG he was a thinker, and he was gay!), it's only fair to consider that trait in the analysis of the work he did...

Three Laws Safe (3, Insightful)

wcrowe (94389) | about 4 months ago | (#47231735)

"Passing" the Turing Test is about as valid as Asimov's Three Laws of Robotics.

Don't be ridiculous, just RTFP (1)

Anonymous Coward | about 4 months ago | (#47231777)

Just read Turing's fucking paper linked in the article. It is clearly about a machine competing with a human to convince a third person that he is the human and that the human is the machine. The interlocutor is promised that he is conversing with both a machine and a human, but does not know which is which. The man vs woman game is just an initial example to make it clear what the game is about. Then Turing goes on to replace the man by a machine, but also implicitly assuming that the interlocutor knows that he now has to decide between a machine and a woman. As for the human side, it doesn't matter whether it's a woman or a man.

That test was solved years ago (1)

maharvey (785540) | about 4 months ago | (#47231823)

So it seems that Turing's test was not won by man or machine, but a synthesis of the two: man + internet

Have a woman program the machine. (1)

gurps_npc (621217) | about 4 months ago | (#47231827)

If a woman programs the machine, then this version of the Turing test should be no less difficult than the accepted version.

Re:Have a woman program the machine. (1)

Immerman (2627577) | about 4 months ago | (#47232157)

Excellent suggestion. And if I recall, was not the first computer programmer even a woman? Ada something or other IIRC, and a close associate of Turing.

Re:Have a woman program the machine. (1)

gurps_npc (621217) | about 4 months ago | (#47232635)

Ada Lovelace Which I got courtesy of Zen Pencil's wonderful chart [zenpencils.com]

Re:Have a woman program the machine. (0)

Anonymous Coward | about 4 months ago | (#47232643)

You're a pal and a cosmonaut.

Alan Turing never wrote about the Turing Test? (0)

wonkey_monkey (2592601) | about 4 months ago | (#47231859)

Alan Turing never wrote about the Turing Test

Didn't he? Wikipedia has this to say:

he proposed a third [version] in 1952. In this version, which Turing discussed in a BBC radio broadcast, a jury asks questions of a computer and the role of the computer is to make a significant proportion of the jury believe that it is really a man.

That sounds like the usual formulation of what get called Turing Tests these days..

One of the people quoted in the article seems a bit confused as well:

“Turing never proposed a test in which a computer pretends to be human,” says Karl MacDorman, an associate professor of human-computer interaction at Indiana University. “Turing proposed an imitation game in which a man and a computer compete in pretending to be a woman."

from which I can only infer that Karl MacDorman doesn't consider women to be human.

Re:Alan Turing never wrote about the Turing Test? (1)

Jeremy Erwin (2054) | about 4 months ago | (#47232029)

from which I can only infer that Karl MacDorman doesn't consider women to be human.

This may have been Turing's position as well....

Re:Alan Turing never wrote about the Turing Test? (1)

wonkey_monkey (2592601) | about 4 months ago | (#47232631)

Oh, right, because gay men are famously misogynistic and never have female friends.

Nice to know they got that time portal from the 1970s open again, though.

Re:Alan Turing never wrote about the Turing Test? (1)

Jeremy Erwin (2054) | about 4 months ago | (#47233097)

From a biography of Alan Turing: [google.com]

Alan could not stand social chat or what he was pleased to call "vapid conversation". What he really liked was a thoroughly disputatious exchange of views. It was pretty tiring, really. You could take a safe bet that if you ventured on some self evident proposition, as for example, the earth was round, Alan would produce a great deal of incontrovertible evidence to prove that it was almost certainly flat, ovular, or much the same shape as a Siamese cat which had been broiled for fifteen minutes at a temperature of one thousand degrees Centigrade.Alan's hatred of "vapid conversation", his fear of "unsafe" women, and the value he placed on the importance of time--that is to say, his own--did not make him the most amiable or helpful of guests.

The author, Sara Turing, his mother, does not suppose Alan Turing to be misogynist. But it sounds as Alan was not terribly interested in understanding the female sex, much less understanding the "ways of women" well enough to imitate them. I may be doing a disservice in quoting a source that infamously does not grapple with Turing's homosexuality [thedailybeast.com] but given that the (original) Turing Test can be misconstrued as analogous to a transgenderist exercise, I feel it's appropriate to question whether Turing was even interested in that sort of thing.

Karl MacDorman says women aren't human (0)

Anonymous Coward | about 4 months ago | (#47231943)

According to the article:

Turing never proposed a test in which a computer pretends to be human,” says Karl MacDorman, an associate professor of human-computer interaction at Indiana University. “Turing proposed an imitation game in which a man and a computer compete in pretending to be a woman.

The real question from this article (1)

operagost (62405) | about 4 months ago | (#47231965)

What the heck is "shingled" hair? Do I go to a barber, a hairdresser, or a roofer?

The Turing Test is a sexbot. (0)

Anonymous Coward | about 4 months ago | (#47231987)

He wanted a sexbot that he couldn't tell was a robot. Classic Turing.

Better? (0)

Anonymous Coward | about 4 months ago | (#47231993)

You don't get "profoundly weird" and "gender specific" being used to describe something that is also "better" too often. Might be a reason for that... maybe "better" isn't the right word for it.

obscure? (1)

AdamWill (604569) | about 4 months ago | (#47232013)

"The details of the Imitation Game aren't secret, or even hard to find, and yet no one seems to reference it."

Except, well, at least four of the stories I've seen on the Turing test this week. It really doesn't seem that obscure.

ew (0)

Anonymous Coward | about 4 months ago | (#47232081)

girls are weird.

profoundly weird.

Well... (1)

azav (469988) | about 4 months ago | (#47232455)

isn't that creepy.

Didn't Chris Hansen of Dateline perfect this? (1)

tlambert (566799) | about 4 months ago | (#47232829)

Didn't Chris Hansen of Dateline perfect this? He's made an entire career out of impersonating underage girls to get guys to show up some place so he can film them in his "To Catch a Predator" series.

Turing Tests aren't Turing Tests! (1)

quantaman (517394) | about 4 months ago | (#47233063)

Anyone holding a Turing Test isn't really holding a true Turing Test. Turing didn't define a duration but it's pretty obvious that five minutes isn't long enough to hold a conversation, it's only long enough to ask a series of questions.

To hold an actual conversation you'd need an hour, maybe more. To last that long the bot would need to learn things about the interrogator just like we learn things when we talk to eachother. A bot that could do that could obviously do a lot more as well.

That's not to say the current Turing Test isn't useful. A successful bot could be applied to customer support systems and give insights into language. But it's misleading to indicate that the current incarnation of the Turing Test is testing what Turing intended.

Sexual dimorphism in corpus callosum's splenium... (1)

Jizzbug (101250) | about 4 months ago | (#47233141)

Research has long proven that women have a different corpus callosum than men (which makes them better information synthesizers), where their splenium has more parallel channels of communication between the hemispheres of the brain (10 to 15 channels, whereas men only have 1 or 2 channels). Swedish researchers have proven that gay men have female-typed corpus callosum's. Turing's Imitation Game could have originated because as a gay man he realized he was better at pretending to be a woman than other men were...

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?