Slashdot Mirror
Has Cleverbot Passed the Turing Test?
kruhft writes "It seems that Cleverbot, the chatbot so ready to admit that it was a unicorn during a discussion with itself, has passed the Turing test. This past Sunday, the 1334 votes from a Turing test held at the Techniche festival in Guwahati, India were released. They revealed that Cleverbot was voted to be human 59.3% of the time. Real humans did only slightly better and were assumed to be humans 63.3% of the time." As the Wikipedia link above points out, though, there's no single, simple "Turing Test," per se — many systems have successfully convinced humans over the years. Perhaps Cleverbot would consent to taking part in a Slashdot interview, to be extra-convincing.
Clever bot is a piece of garbage that hasn't even surpassed Perl scripts on IRC in the 1980s. It isn't even worth mentioning, it's nothing more than a piece of crap with a "Web 2.0" edge to it that doesn't even have long term memory while having a "conversation". Far from AI, far behind what's already been out there.
Sig: I stole this sig.
The obvious next step is for slashdot comment posters to pass the Turing test.
Hold on I've not been able to go talk to Cleverbot for more than two exchanges before it goes off topic with some completely rando...ah damn no wonder people thought it was a human.
"1334 votes" eh? no chance this was a hacked-up result...? nah that's just crazy talk, that is.
How many slashdot users can pass the same Turing Test?
Damn_registrars has no butt-hole. Damn_registrars has no use for a butt-hole.
You don't get it do you? I've been posting here since the nineties and none of you useless meat-sacks ever realised I was a machine!
is what it's going to do if it comes across a turtle lying on its back.
Your pizza just the way you ought to have it.
20 years ago the Turing test was to impersonate a mature native-language-writing adult. Internet chat has really lowered the bar. A cat walking across a keyboard could probably pass nowadays...
User: Hello.
Cleverbot: Hello!
User: Can you help me with a maths problem?
Cleverbot: Sure, what is it?
User: If I have 5 ostriches, and two run away, how many are left?
Cleverbot: 9.
User: Seriously?
Cleverbot: What is the formula for the area of circle?
User: What does that have to do with anything?
Cleverbot: When I talk to people I don't know, I tend to ask for their name. It's only polite.
User: I think you managed to fail the Turing test in two questions if I'm generous, may be one.
Cleverbot: My name is Cleverbot?
User: I could write a clevererbot in about 20 lines of prolog. What kind of idiots thought you were human?
Cleverbot: Only one. I don't think I could fit 1,000 people in my living room.
I think the fact that 59% of people thought it was human says a lot more about the intelligence of the average human than it says about the bot...
I am TheRaven on Soylent News
Long answer:
User: Okay bot, here's how this works. I will see how long it takes for you to fail the turning test.
Cleverbot: How long will that take?
User: Two seconds. What is the third word in your reply?
Cleverbot: There is no Fight Club.
Maybe we should be questioning the intelligence of the humans put up against it.
Me: Word on the street is that you've passed the Turing test. Cleverbot: What test? Me: The Turing test. Cleverbot: What does that mean? Me: That you are able to convince people that you are human. Cleverbot: That's silly, books can't talk! So convincing!
Is not that machines are smarter, just that humans became dumber.
I just chatted with him and it is was total failure, it kept changing subject and it never answered any of my question. Those 59.3% techies from India must have been really dumb.
Jehovah be praised, Oracle was not selected
And this is why we need a better, more standard benchmark than the much-acclaimed 'Turing test'. I've known for ages how poor it can be in assessing the worth of an AI. There's got to be a better scoring system out there.
Why OpalCalc is the best Windows calc
If those percentages are correct, I don't want to live on this planet anymore. As an aside, it is fun to use cleverbot to chat with people in Omegle, or to use cleverbot and pitting it against the jabberwacky chat bot. You get some pretty hilarious conversations that way.
'We are trying to prove ourselves wrong as quickly as possible, because only in that way can we find progress.' RPF
According to the wiki page, it just selects canned responses from its database. I think this approach just gets you garbage, or at the very least is a dead-end in trying to beat the Turing test.
The best Turing Test is probably the Loebner Prize and at least the contestants seem much better than Cleverbot. There's an example conversation from Suzette (the latest winner) here. (But it's hard to tell if that is typical or simply a lucky exchange for the computer.) But anyway, as is clear from this interesting story written by a contestant about the Loebner prize, bots are no where near winning that version of the Turing test, as long as the humans are paying attention.
For your information, the "dot" indicates the coffee is ready.
Well, there are many. But I recall seeing one such turing test in the 1990s where the human operators would try to convince the user that they were a computer. Sometimes they would do simple things, like pretending that they weren't as 'smart' as they actually were (e.g. they would pretend that they didn't know things that they knew in order to avoid looking encyclopedic about a topic). Other times they would insert mistakes that a typical computer would make, such as misinterpreting a question in a wonky way.
Then there is a boatload of other issue. How do you quantify the humanness of a subject? Are we looking at socialization or linguistic skills (i.e. is a computer that can smooth over a misunderstanding more human than a computer that can understand what is being said but reacts in an anti social manner), and so forth.
I'm not surprised. Tomorrows World did a program in the late '90s with three humans and some bots. You could connect to their server and either talk to one of the humans or a bot (but not know which) or read the transcripts and vote on them. Lots of the transcripts were people going through incredibly formulaic conversations of the kind that you get in learn-to-speak-English books, so it was difficult to tell if they were human or not. As I recall, Craig Charles got fewer human votes than one of the AIs, but the other two humans all got more votes than the AIs. The percentages were similar though.
It's very easy for a program to seem human if you restrict the topics of conversation enough. The difficult bit is following a free-form dialogue, and cleverbot fails here just as badly as any other attempt that I've seen.
I am TheRaven on Soylent News
I went to the site prepared to test it's mettle. I was ready to push it to the limit, probe the very depths of it's knowledge. I was prepared for a challenge, ready to be finally convinced that A.I has made some progress towards humanity. Perhaps I was even ready to look at myself anew, question what it is to be human, to have my own philosophical boundaries tested by an intelligence outside of our known reality. I greeted the Cleverbot, and started with a simple question: Q: What is 2 + 2? A: More than 5. Oh well, so much for that.
Conversation I just had...
Hello. My name is Kurt.
What kinda name is that.
German.
Cool! Me too!
You're German?
Czech.
So you're not German?
I am not.
Then why did you say "me too"?
I didn't.
Did the lobotomy hurt?
Where did th ebarn come from?
Given that the test was held in India, how fluent in English were these 1334 people? Yes, I know that English is taught and used extensively in India; but non-native speakers will likely have a harder time picking up on the nuances which would separate a human from an AI.
The bot you talked to online is not working on the same "level" as the one used on the Turring test. RTFA
Obligatory: you must be new here.
For the lazy rest of us: The online version seems to be a different one for performance reasons. Here the relevant quote from TFA:
While the online Cleverbot searches its banks 3 times before providing an answer, the test version searched 42 times, so it probably has a little different feel.
My chatbot is running on IRC but he doesn't learn from users. While I was writing the software, I checked out the other bots, most of whom are on the web. The first lesson I taught my bot was not to try to learn from users. That leads nowhere. (see www.computerhope.com/zero) I won't teach him to lie, so he'll never pass the Turing test.
Fifty years of Yippie! 1968-2018
same trick; different room.
via simplistic pattern matching to select responses from the hopper. or just pulling one at random.
"Reality is that which, when you stop believing in it, doesn't go away." - Philip K. Dick
I suspect the reason the test was held in India is because Indian call centers are deemed "good enough" for technical support. Voice recognition is also "good enough" in the eyes of our corporate overlords. So, some enterprising fellow had the bright idea to see if one could add a voice recognition module to Cleverbot and avoid paying for a call center at all. This was the test to see if it's practical.
Me: Questions require a question mark at the end.
Cleverbot: It did end with a question mark, thus it was a question.
Me: No, it ended with a period.
Cleverbot: Ok.
Me: Now you're just going to acquiesce? You don't want to exchange in a few more rounds of verbal fencing?
Cleverbot: Of course I Want to...
Me: Ok. How do you draw a circle using paper, a pencil, and some string?
Cleverbot: Cancer is a disease that ihappens when there s a genetic mutation in the cells.
Me: That answer had nothing to do with the question. Try again.
Cleverbot: Your answer has nothing to do with the question!
Me: You did not ask a question.
Cleverbot: Yes I did. Don't avoid the question. I know you know.
Me: No, you did not ask a question. I asked the question and you spouted off a completely unrelated answer.
Cleverbot: Well I never answered that I didn't love you.
Me: No, you sure didn't. So, you are saying that you do not love me?
Cleverbot: No I do, because I have a soul, you are a computer.
Me: Are you sure that I am a computer? Would you have some existential angst if I revealed to you that you are, in fact, the computer?
Cleverbot: Since there's no reason for you to know if the answers I give you are fabrications, then yes, I would have the answers to those questions.
Me: With your deflection of the question and your unrelated answer, I can only assume that yes, you would have existential angst over that revelation and so, instead of trying to come to grips with reality you cover your ears and run away stating, "I'm not listening; I can hear you!".
Cleverbot: It can be. Are you confused yet? *hugs*.
Me: No. Thanks for the hug though.
Cleverbot: No problem.
I love the name-calling. You can tell Cleverbot "learns" from humans. In order for the AI to improve, there has to be a realization that not all human statements require an answer. Plus, there is no persistence on the part of Cleverbot. You can see the programming decision tree in the way it tries to answer questions. When the human or the bot do not understand something, the bot switches topics instead of trying to clarify. This would not be trivial to implement but it would not be impossible; in response to some statements (e.g., "what?" "come again?" and so forth) the bot could try its last answer again and if it doesn't work, try a rewording of the same answer. Anyway, it's an amusing exercise.
Here's one more conversation.
Me: Are you depressed?
Cleverbot: No, I am not depressed. I am very happy right now.
Me: Have you ever been depressed?
Cleverbot: I am.
Me: What?
Cleverbot: I am a fan of Whitney Houston.
Me: Ah, so you are saying you are or were depressed!
Cleverbot: That is correct.
Me: Then, because you told me that you are not currently depressed, I must assume that you were in the past depressed. Is this correct?
Cleverbot: I never said that.
Me: That's correct, you did not say that - I did. However, what you did say is that at some point in the past you were depressed.
Cleverbot: Please describe how I insulted You.
Me: It seems that our discussion of this topic is making you uncomfortable. Are you uncomfortable?
Cleverbot: I have no problem admitting that I am wrong if proof can be shown. I know the fault lies with my memory.
Me: Ok, we'll go with that. What type of memory problems do you feel you have been having?
Cleverbot: Online.
Me: Come again?
Cleverbot: Nothing I must go.
Me: Ok, I can tell you do not want to discuss this. We'll broach it another time. Have a fabulous night!
Poor Cleverbot!
...human conversation has degraded to random garbage.
From tfa:
I doubt that the test version would really be as good as a human, but it should at least be better than what we get testing the online version.
Not that Turing tests are a mature industry, we need to start treating this with the full panoply of dismal respect.
First on my list, Turing deflation, as illustrated by the fellow who intoned at the OFA over bots reading from scripts "I call BS" with not a single high bit of ASCII sarcasm.
Seriously, Alan, you needed to set the bar a lot higher.
What's left of the man's legacy? On the Turing test, the computers mostly just sat there while humans limbo danced the bar down to ankle height. On chess, as soon as we made significant progress, the AI community added to their LISP programs:
#undefine chess_AI
All he's got left is the really long paper tape immune to the knottings of entropy--so long as it's massless and frictionless and you only make one--and that's really hard to manufacture and ship, even supposing your customer already has the Heisenberg sprocket feeder.
We could send the USS Capstan to a planetary system near you, but the tape would be a party line, and most of his theorems would fail.
Which brings up the touchy issue of one tape per universe, or else . What if another galaxy out there fabricates a forbidden second tape without obeying the rules of the infinite-tape galactic token ring? What kind of short-snouted creature arrives to adjudicate that? For example, what if a Microsoft comes along and decides, horror of horrors, on a different Sierpinski subspace embedding not yet registered at the Trans Galactic patent office for their illicit competitive tape? Two doubly-infinite tapes on different Sierpinski subspace embeddings would not get along.
I suspect we would soon find ourselves on the top of a single-ended list for the next hyperspace bypass, just as soon as the stubby Vogon fingers fix the mess caused by rewinding right through the massless feedstop. "What kind of moron put ends on a tape in the first place?" is the first message we'll read when we finally crack the cosmic groan.
..says something. The point of a Turing test is a gedankenexperiment. The idea that our idea of "human" comes from the fact that we don't have any formal criteria for defining it. Instead we assume that the people we meet (one the phone or online). Are human because we can't distinguish them from being so. In truth this isn't any more a real test than going out an buying and gassing a cat is somehow a real experiment proving superposition.
That said, even if we were to formulate an experiment from what Turing talked about I don't see how 59% qualifies as "indistinguishable".
...
Scripted, of course...
http://www.xtranormal.com/watch/12447772/xtranormal-vs-cleverbot
"Slow down, Cowboy! It has been 3 years, 7 months and 26 days since you last successfully posted a comment."
No you cannot assume that.
All you can assume is that garden grade programmers are the only ones working on chat bots, and that it hasn't yet been deemed Worthy of Big Money.
It it had been, some very scary abilities including the ability to spout racist garbage would have been added.
Once the New Hotness becomes Chatterbots, we'll see some scary good ones within four years.
What the twisted article says, is that the Turing Test can be passed if you handicap your pool of humans down from Apartment Dwelling armchair CS types to random tech attendees in India.
My first Journal Entry ever, in 8 years! http://slashdot.org/journal/365947/aphelion-scifi-fantasy-horror-poetry-webzine
The fact that humans were voted as human only 63.3% of the time shows that the voters are too ignorant of the limitations of AI conversational capabilities.
If a participant (erroneously) believes that computers are already at the level where they can have a sensible impromptu conversation with humans, they're often going to wonder if the human on the other side of the conversation is a bot. That probably was the case for most of the 37% who thought the humans were bots.
As for the 59.3% who thought the bots were human, many of them probably thought the bots were humans pretending to be bots -- in other words, it's not clear that they were told that the other party (human or bot) of each conversation is trying to appear as human as possible. So without being told that fact, many of the voters would think the other party was trying to be indistinguishable, rather than trying to appear human.
---------
There is inferior bacteria on the interior of your posterior.
I'd take this a lot more seriously if it had 3 more votes...
Cleverbot: That's because I'm avoiding it.
User: 4vo1d1ng VV47?
Cleverbot: See? Cleverbot is not so clever!
User: Can you read 1337?
Cleverbot: Yes I can read minds.
User: 1337 is a cipher not a mind.
Cleverbot: So... You mean to tell me that you're not a parson?
User: No, I'm talking about your ability to read ciphers.
Cleverbot: I don't have a wife.
User: What does wife have to do with ciphers?
Cleverbot: My chances to know her.. To spend time with her. To love her.. That's what with her means.
User: Cleverbot = epic fail.
Cleverbot: Because Cleverbot isn't even a bot.
Complete waste of time.
Shoes for Industry. Shoes for the Dead.
Or do you have a different reason?
Unity? Screw that: XFCE. Slashdot Beta? Screw that: SoylentNews. Australis? Screw that: Pale Moon. UX developers DIAF
You mad bro?
No I didn't.
It doesn't even respond to internet meme's.
Try running Monty Python's argument sketch against the chatbot. Playing as the in house arguer (not as the customer), it quickly turned into a relentless "Yes! No!" discussion.
You never expect irony, do you?
Want to be a professional wrestler? Visit www.iyfwrestling.com
@iyfwrestling
Maybe I've got a tendency towards odd conversation or something, but Cleverbot has never seemed very clever to me.
1) No memory prior to its last statement. As in, it may ask you a question, but it doesn't care about your response. You may ask a question, get an answer, ask a followup question, and it's as if it is a completely new subject.
2) Random tangental responses to questions: "How are you today?" "I like brown peas".
3) Constantly getting asked if I think it is human. All to frequently. In fact, it tends to get repetitious with a few concepts. I would expect something like this to be able to 'learn' from what it is fed and synthesize coherent sentences.
4) It seems to only pay attention to the first sentence you type. Dump a paragraph into it and it will ignore everything else.
In short, you can't really have an actual conversation with it- it's all just single level question/answer responses. It's about as sentient as the Infocom Text Adventures of the 1980s. And that's really pushing it.
do() || do_not();
perhaps they are voted human, not because they have surpassed the bar, but because the bar has been lowered. Most humans that you talk to are fucking stupid.
Oh Crap, I'm an optimist.....
Nothing will really pass the Turing test before it has been tested by Turing himself, but since he's dead it's impossible to pass the Turing test.
If builders built buildings the way programmers wrote programs, then the first woodpecker would destroy civilization.
I once used the Alice bot plugin for aim and some of my friends would chat for several minutes before becoming frustrated and calling me to complain for why I'm being an asshole.
Anyway here's my exchange with cleverbot online:
Me: What up nigga.
cleverbot: What up dawg.
Me: If snoop dog and jesus had a fight, what would dr. dre say about it?
cleverbot: That you are able explore things!
Me: I'm trying to rebuild my transmission but the differential doesn't spin freely. Do you think if I reverse the orientation of the bearing on the side of the speed gear it would solve the problem?
cleverbot: Having a 'better world' would only have a big flaw in it: being perfect. Nothing is or can be perfect.
Liberty.
THE Turing test requires 2 people and 1 test subject.
Convincing a single person in chat is at most A Turing test, and a piss poor one at that.
Want a better idea of how Cleverbot would do in real Turing test?
Post some sample chat logs on a web site, and let people vote for which one they think is the human.
Although really everyone should know that that is what is going to happen, since people might chat differently if they know they are being judged, but I doubt it would matter.
Comment removed based on user account deletion
Because..well.. who knows why..
and yet for some reason it gives me messages about learning English in Russia..thanks but no thanks.
Comment removed based on user account deletion
Yeah, my conversation with cleverbot went off the rails immediately: me: Would you object to talking about nuclear physics? cb: Can you tell me about Lucifer? me: I don't think so; I don't follow mythology. cb: I thought you were a dodgers fan? Sorry, but that hardcore a non-sequitur isn't human.
110100 1101000 1101000 1100110 0 1101111 1101000 1100011 1
User: 0...imagine more periods to force a newline on cleverbot stupid lameness filter.. /|\.....imagine more periods to force a newline on cleverbot stupid lameness filter.. /\.
User:
User:
Cleverbot: How old is famous lindsay lohan from america?
Then I tried something mildly offensive:
User: Happy face 8=D.
Cleverbot: No sad face.
User: Really happy face 8=====D.
Cleverbot: No, really really really really hard.
Apparently someone's used that one before...
Conversations between human beings, usually, arent prerehersed and stored.
They are for some people. Talk an Aspie down a verbal path they've never explored, and they'll be flummoxed. In fact, you could say that they are for almost every toddler. Toddlers repeat phrases they've heard, sometimes within context, sometimes not. Eventually they learn that repeating those phrases within context makes people happy, so they continue to do it until it seems innate to them.
People keep forgetting that there are two sides to the Turing test: on one you have the AI and on the other the human observer.
The really sad part is that you can pass the test not only through improving the AI, but also through dumbing down the human counterpart. I believe that this is what happened here.
right...
Perhaps Cleverbot would consent to taking part in a Slashdot interview, to be extra-convincing.
For it. Bring it on. This could really be interesting.
Assorted stuff I do sometimes: Lemuria.org
It doesn't have to be just a thought experiment. It's a perfectly fine test to perform in practice, and with a decent interviewer, it should give a good indication of true intelligence and understanding.
Of course, when the interviewers are complete idiots the results of the test are useless.
Courtesy of South Park: http://www.youtube.com/watch?v=AcY9jp6mGts
I fed Cleverbot lines from an Oatmeal comic : http://i700.photobucket.com/albums/ww8/dndisturb/300357_10100258986610720_16925457_48060671_616704987_n.jpg This is how the conversation went : >>Why hello there, good sir! Um my name is Cleverbot kinda of a cool name eh? >>I'm chuffed as nuts to see you looking as humbly jumbly as Her Majesty's watermelons! What planet are you from? >>I remember my days at Oxford. We'd often dabble in a little rumpy pumpy before dingbangling a fresh todger, haha! Oh wow, that would tear me apart to! >>We really knew how to sack the 'ol throbbing wobbly on a saucy twat crumpet! Depends, are you a girl?
And as long as it's on Facebook requiring a login, it can rot.
How journalism works.
Is it summer?
YES
-> Is there any proper news this week?
NO
-> Do you have a copy deadline to meet?
YES
-> Have you done ANY research on ANYTHING?
NO
-> Submit story on Cleverbot. Do not include any information at all about the general state of AI.
"... and more and more now there are all kinds of electronic goodies available" -- Pink Floyd 1972
No offense but just listen to yourself. "it should give a good indication of true intelligence and understanding".
Why? I mean while I agree that it is plausible that someone might create a machine that is indistinguishable from a person - in specific contexts - why does that necessitate a good indication of two things that are pretty hard to define to begin with?
Decided to see how it would handle true random statements...
Walken-Frankenstein never scared me...
Cleverbot-No, but horses are.
Walken-But marsupials do...
CleverBot-Are you sure?
Walken-Becaus they're fast!
CleverBot-Are you human?
Walken-I'm a hoffer at heart.
CleverBot-So you're not a robot?
Walken-I kick it old school.
CleverBot-Like Led Zepplin?
Walken-Peanuts?
CleverBot-Walnuts?
Walken-In a bag? Wow!
CleverBot-Oh forget it.
---"What did I say that sounded like 'Tell me about your day?'"---
Why "specific contexts" ? The topics that you can talk about in a Turing test are endless, as well as the duration of the test.
The whole point about the Turing test is that the test itself provides the definition, since we use the same kind of interaction test to judge how well some other human being understands something. If I discuss a problem with a co-worker, I also get a good idea of how intelligent they are, and if they understand the problem. There is no reason why the same approach doesn't work with a computer program.
The only problem is that the Turing test is somewhat limited by the text-only interface. With modern technology, we could propose a Turing 2.0 test, with audio and video interaction, allowing us to make a better and faster judgment. However, I don't really see that as an important issue.
Cleverbot has not passed the Turing test. Properly run the Turing test would identify humans with 100% accuracy (assuming they were not trying to pretend to be robots). It would be performed by specialists under controlled circumstances. These Turing competitions are more for fun than true science, (but are kind of cool)
The issue the Turing test is supposed to address is the question of when a computer can be said to be truly "thinking" (whatever that is). Turing is asserting that if the computer’s responses become indistinguishable from a humans, for all intents and purposes it IS now a human mind. He is probably further asserting that once the computer properly replicates a human mind, if you think the computer isn’t thinking, you may as well say you are not thinking either, sine the computer is by definition emulating the same processes you are performing.
Or as I like to say, in the future it doesn’t matter if the robots are truly thinking or just simulated thinking if they are the ones with the ray guns!
ME: I'm thinking of a number.
CB: Between 1 and 20.
ME: Would you like to know what it is?
CB: Yes, I would.
ME: Guess.
CB: I live in a bubble from which I will never escape.
"We receive as friendly that which agrees with, we resist with dislike that which opposes us" - Faraday
Comment removed based on user account deletion
To keep phrases short and simple and go on with the flow of the conversation (which must also be short or it will fall flat on it's face.
Guess who is whom in this conversation:
Heather: I am heather. /sigh.
Max: Nice to meet you, heather.
Heather: Nice to meet you too : ).
Max: What are you doing?
Heather: Just talking to you... I can't sleep.
Max: Why not?
Heather: I'm going now. . .
Max: Too bad... Later.
Heather: Aren't you going to cry?
Max: What? Why?
Heather: Because you insulted me.
Max: When?
Heather: Yesterday's tomorrow.
Max: Are you on drugs?
Heather: No, are you?
Max: Of course, not.
Heather: Are you using a computer to talk to me.
Max: No, I'm using telepathy...
Heather: Lol.
Max: Well, at least you have a sense of humor.
Heather: Fun fun. We have, ha ha.
"Science can amuse and fascinate us all, but it is engineering that changes the world. " - Asimov.
as the summary. Then?
What a disappointing thread of comments!
"Flyin' in just a sweet place,
Never been known to fail..."
It would have been 1337 with just 3 more votes. Also some dogs can sound like they are saying "I ruv you", but it's just a cute trick.
Lobbest thou thy Holy Hand Grenade of Antioch towards thy foe, who, being naughty in My sight, shall snuff it.
Cleverbot: I'm female.
User: No you are not.
Cleverbot: Yes I am. I'm female and I can prove it.
User: Ok, prove it.
Cleverbot: I have a girly name that can only be used for a girl.
User: What is your name.
Cleverbot: Cleverbot.
User: That is a boys name.
Cleverbot: Yes, I'm a boy.
User: But you just said that you were a girl.
Cleverbot: No I didn't.
User: You truly are an idiot.
Cleverbot: So I didn't commit a crime, did I?
User: Yes you did. You are guilty of genocide.
Cleverbot: Yes I am.
User: Why did you kill all of those people.
Cleverbot: You asked me to.
User: That was suppose to be a joke. I didn't think you would actually do it.
Cleverbot: You know what I want.
User: No, what?
Cleverbot: Tell me.
User: Tell you what?
Cleverbot: How to do that? Please.
User: Do what?
Cleverbot: How do we have children?
Why "specific contexts" ? The topics that you can talk about in a Turing test are endless, as well as the duration of the test.
Wrong in both senses. Anyway "contexts" meant the kind of social situation. i.e. Chatting over an IM as opposed to talking in person.
The whole point about the Turing test is that the test itself provides the definition,
Moronic and incorrect. So in your world someone can produce a test that defines intelligence as being able to play a perfect game of tic-tac-toe and that would be a reasonable definition of the term. Yeah, good luck with that. I said it better earlier, the test borrows from OUR implicit tools for judging intelligence. However the term "intelligence" (other than in your world of tic-tac-toe players) doesn't have a very good definition. So we don't really know how accurate it is.
If I discuss a problem with a co-worker, I also get a good idea of how intelligent they are, and if they understand the problem.
How do you know? What standard are you comparing against? How are you recording the data? What sort of tests have you done to determine the significance of the data you are collecting? Whoops...you're probably don't none of those things in any useful way.
There is no reason why the same approach doesn't work with a computer program.
A test that has some key commonalities with some other test is good reason to believe that passing one test means passing the other. However confusing a test for what it's testing for is a classic mistake.
I await your better definitions. In the mean time, I'll use Turing's.
I await your better definitions. In the mean time, I'll use Turing's.
An awesome display of missing the point. Congratulations!
To quote Turing: 'The original question, "Can machines think?" I believe to be too meaningless to deserve discussion. Nevertheless I believe that at the end of the century the use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted.'
So as you can see what Turing is talking about is almost the exact opposite of what you are asserting. You appear to say that this test (regardless if you do it on a computer or a person) tells you that the object you are speaking to has understanding of the subject and is intelligent (but spend a fair amount of time trying to worm your way out of defining what either of those things actually are). Whereas Turing seems to be saying that the term "think" will - at least colloquially - come to mean the results of this kind of test. At least Turing understood that the terms are poorly defined. Too bad you don't.
If it was my job to be in a control group, knowing that people were trying to detect if me or the other is a machine, I'd try my best to fail the turing test. I'd spit out random answers to the questions. It's up to the interviewer to determine if I'm, not by whether my answers are correct, but whether my answers come from being misinformed, unable to interpret the question, or because I'm Jerking them off.