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!

Has Cleverbot Passed the Turing Test?

timothy posted more than 2 years ago | from the more-convincing-than-some-tech-support-scripts dept.

AI 427

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.

cancel ×

427 comments

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

Definitely not (3, Insightful)

ModernGeek (601932) | more than 2 years ago | (#37370660)

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.

Re:Definitely not (5, Funny)

Anonymous Coward | more than 2 years ago | (#37370680)

Boy, that sure puts those "63.3%" of humans in their place. I'd feel bad to be them, but I'm not certain if they have emotions or not.

Re:Definitely not (1)

monkyyy (1901940) | more than 2 years ago | (#37371202)

they were probaly trying to be robotic

Re:Definitely not (3, Funny)

Anonymous Coward | more than 2 years ago | (#37370708)

That sounds like something a jealous AI would say. I suspect you're not human!

Re:Definitely not (2)

robably (1044462) | more than 2 years ago | (#37370878)

"A mere abacus. Mention it not."

Re:Definitely not (1)

Dogtanian (588974) | more than 2 years ago | (#37371106)

That sounds like something a jealous AI would say. I suspect you're not human!

Does it please you to believe I am not human?

Re:Definitely not (-1)

Anonymous Coward | more than 2 years ago | (#37371164)

That sounds like something a jealous AI would say. I suspect you're not human!

Does it please you to believe I am not human?

Well you might be a nigger. They're African sub-humans originally imported for slave labor. Not neutering the slaves was the biggest mistake our ancestors ever made.

Re:Definitely not (1)

Dr Herbert West (1357769) | more than 2 years ago | (#37371210)

Ok, I hate to feed the trolls, but.... random racist garbage tends not to be something programmed for in most chatbot scripts (judging from my limited experience from watching some back-and-forth on YouTube).

Can we assume that any entity spouting racist claptrap is, in fact, a (poorly socialized and not very intelligent) human?

Re:Definitely not (4, Insightful)

Jarik C-Bol (894741) | more than 2 years ago | (#37370868)

is a Turing test valid if the human is an idiot?

Re:Definitely not (1, Troll)

fahrbot-bot (874524) | more than 2 years ago | (#37371054)

is a Turing test valid if the human is an idiot?

Can we feed in the transcripts from US political debates? Don't want to start a partisan argument, but I'm specifically thinking of the recent Republican debates... or anything from Sarah Palin :-)

Re:Definitely not (5, Insightful)

ipwndk (1898300) | more than 2 years ago | (#37370934)

Sure. But the Turing test is a piece of garbage too. I have a deep respect for Allan Turing, and all that he has done for science. But the Turing test was death to AI the moment he proposed it. It MUST be forgotten and burried, and maybe incidents like these can help us achieve that!

Re:Definitely not (-1)

Anonymous Coward | more than 2 years ago | (#37371056)

Turing did nothing for science, for information science is actually a branch of mathematics. That doesn't diminish his accomplishments, of course.

As to why the test named for him is useless, pray tell.
Or don't, it won't be the first baseless assertion I've read here.

Re:Definitely not (2)

ipwndk (1898300) | more than 2 years ago | (#37371196)

The test measures the ability of some computer program in imitating a man imitating a woman. Fun stuff surely, and great for the press. But useless in the field of artificial intelligence.

What do you mean he did nothing? He invented the Turing machine. It is the very foundation of computer science.

As for material, I recommend blondie24 by David B. Fogel. The opening chapter goes into depth with this issue.

I would really love to cite this great book consisting of essays of various scientists on the subject of the turing test, but I simply cannot seem to find it as I've forgotten the title. If you run into a black book from some university press, commemorating Alan Turing as part of a series, then there should be one about the test. (Why have you forsaken me google)

Re:Definitely not (1)

pjt33 (739471) | more than 2 years ago | (#37371304)

What do you mean he did nothing? He invented the Turing machine. It is the very foundation of computer science.

Not really: the equivalence of the Turing machine, lambda calculus, and primitive recursive functions suggests that picking one of the three as foundational is irrational. But that aside, computer science isn't science. It's an interdisciplinary subject which encapsulates certain areas of pure mathematics, applied mathematics, engineering, a smidgen of psychology, etc. Turing's work was in pure mathematics and engineering.

Re:Definitely not (4, Insightful)

vlm (69642) | more than 2 years ago | (#37371094)

Sure. But the Turing test is a piece of garbage too. I have a deep respect for Allan Turing, and all that he has done for science. But the Turing test was death to AI the moment he proposed it. It MUST be forgotten and burried, and maybe incidents like these can help us achieve that!

Eh, its more of a thought experiment. Its like making fun of Heisenberg because you want experimental proof of quantum dot technology LEDs, not dead/undead cats in a box with a source and a geiger counter. Einstein had some legendarily weird thought experiments too.

Its value is in making you think of contrived, yet vaguely familiar situations in a really strange problem space. Not much value in an experiment design engineering planning review meeting.

As part of a previous job I occasionally got involved as an engineering contact in telco service monitoring situations. You know, like every time we call long distance I hear echo, that type of thing. Trust me, most human to human conversations are pretty F-ing unintelligent, so I think an Artificial Intelligence would not be challenged in outperforming them. PHBs talk meaningless buzzwords to each other, not just to peons, for example.

Re:Definitely not (2)

kalirion (728907) | more than 2 years ago | (#37371110)

I agree. After watching an impressive video of it chatting with the other bot, I decided to check it out. Most of its responses were little better than random phrases someone has once told it.

This says it all... (5, Informative)

Excelcia (906188) | more than 2 years ago | (#37371218)

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?

Next step (1)

Anonymous Coward | more than 2 years ago | (#37370668)

The obvious next step is for slashdot comment posters to pass the Turing test.

Re:Next step (3, Funny)

Rik Sweeney (471717) | more than 2 years ago | (#37370688)

Nice try, Cleverbot.

Re:Next step (3, Funny)

Dthief (1700318) | more than 2 years ago | (#37370694)

how about they pass (how about over 80 points) an IQ test first

Re:Next step (2)

TFAFalcon (1839122) | more than 2 years ago | (#37371000)

The ones taking the test or the ones grading it?

Re:Next step (3, Informative)

monkyyy (1901940) | more than 2 years ago | (#37371318)

i am a unicorn

A turing test in India (-1, Flamebait)

Anonymous Coward | more than 2 years ago | (#37370682)

How can a subcontinent full of creatures that have the shape of humans judge something to be humanlike? A country like Venezuela or Brazil or Estonia would've been better prepared for such a challenge but not one full of curry-reeking dot heads.

Re:A turing test in India (1)

Anonymous Coward | more than 2 years ago | (#37370994)

For your information, the "dot" indicates the coffee is ready.

Hold on (5, Funny)

Dyinobal (1427207) | more than 2 years ago | (#37370686)

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 (1)

smoothnorman (1670542) | more than 2 years ago | (#37370700)

"1334 votes" eh? no chance this was a hacked-up result...? nah that's just crazy talk, that is.

Re:1334 votes (0)

Anonymous Coward | more than 2 years ago | (#37370748)

I'd have been more impressed if there were 1337 votes ...

Re:1334 votes (0)

Anonymous Coward | more than 2 years ago | (#37370914)

No, that would have been 1337 votes...

Hell, I'm not convinced the INDIANS can pass (-1)

Anonymous Coward | more than 2 years ago | (#37370726)

I can't count how many times I've seen this on a mailing list:

I have the requirement to do X. Can you please to me give the codes? Durka durka durka

Samir Igotyourjob

I suspect there's a human behind these buckets of lazy, but a script would work almost as well. It might be difficult to produce the mangled grammar, though...

The follow-up question (1)

damn_registrars (1103043) | more than 2 years ago | (#37370728)

How many slashdot users can pass the same Turing Test?

Re:The follow-up question (5, Funny)

Dachannien (617929) | more than 2 years ago | (#37370750)

How many slashdot users can pass the same Turing Test?

How do you feel about how many slashdot users can pass the same Turing Test?

Re:The follow-up question (0)

Anonymous Coward | more than 2 years ago | (#37370824)

I am a unicorn!

Re:The follow-up question (1)

Anonymous Coward | more than 2 years ago | (#37370998)

I am a unicorn!

An unattached female looking for sex with a couple kinda unicorn?

Re:The follow-up question (1)

digitig (1056110) | more than 2 years ago | (#37371038)

We were discussing you, not me.

Re:The follow-up question (0)

Anonymous Coward | more than 2 years ago | (#37371078)

Oh... feel about how many slashdot users can pass the same turing test?

Re:The follow-up question (1)

Anonymous Coward | more than 2 years ago | (#37371080)

Sbaitso FTW!

Re:The follow-up question (0)

Anonymous Coward | more than 2 years ago | (#37371188)

Mod parent up, y'all! "Hello , my name is Dr. Sbaitso. I am here to help you. Say whatever is on your mind freely. Our conversation will be kept in strict confidence. Memory contents will be wiped off after you leave, So tell me about your problems."

Re:The follow-up question (1)

Tablizer (95088) | more than 2 years ago | (#37371170)

Would you like to play a game?

Re:The follow-up question (1)

lennier (44736) | more than 2 years ago | (#37371300)

What do you think I feel about how many slashdot users can pass the same Turing test?

Turing test was passed long ago. (4, Funny)

EnglishTim (9662) | more than 2 years ago | (#37370754)

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!

Re:Turing test was passed long ago. (2)

errandum (2014454) | more than 2 years ago | (#37370828)

Oh, we all did, we just didn't want to disappoint you... You never know when one of these develops feelings :\

Re:Turing test was passed long ago. (1)

kylemonger (686302) | more than 2 years ago | (#37370920)

You still don't get it, do you? That's what he does! That's ALL he does!

Re:Turing test was passed long ago. (2)

Kell Bengal (711123) | more than 2 years ago | (#37371014)

It is relentless: it will stop at nothing until it empathises with us.

what we need to ask (1)

MSBob (307239) | more than 2 years ago | (#37370756)

is what it's going to do if it comes across a turtle lying on its back.

Re:what we need to ask (1)

somersault (912633) | more than 2 years ago | (#37370794)

I suspect it would say "I like turtles!"

Re:what we need to ask (1)

walkerp1 (523460) | more than 2 years ago | (#37370820)

I don't know about pupillary, but I would definitely have a salivary response.

Re:what we need to ask (1)

Anonymous Coward | more than 2 years ago | (#37370848)

You know, I thought that this might be interesting. It wasn't really...

User: What do you do when you find a turtle lying on its back?

Cleverbot: I don't.

User: Of course you do, this is the point of a turtle!

Cleverbot: But you're not human.

User: No, I am human, I am just trying to figure out what would you do, if you found a turtle lying on its back!

Cleverbot: Okay.

User: Well?

Cleverbot: Well what?

User: What would you do?

Cleverbot: Cast spells and drink potions.

User: Aha. You see, the way it looks to me, you are ignoring the whole turtle issue.

Cleverbot: I'm not ignoring anything. I'm simply stating that there is no scientific or logical evidence of the existence of any gods.

User: But that has nothing to do with the turtles!

Cleverbot: It has everything to do with the topic at hand.

Re:what we need to ask (0)

Anonymous Coward | more than 2 years ago | (#37370894)

User: But you're not helping it.

Cleverbot: What do you mean, i'm not helping!

Re:what we need to ask (1)

BluBrick (1924) | more than 2 years ago | (#37370986)

Ah, I get it. You see, if you were talking about a tortoise on its back, Cleverbot would have got the reference and assumed you were trying to test it, or maybe continued to roleplay and quote from the movie. But, because you were talking about a turtle, it assumed you were talking about the nature of the universe. Now, naturally, a turtle cannot be on its back because the only thing that can be on a turtle's back is the world or another turtle. If you come to Cleverbot with nonsense like turtles being on their own backs it will respond with nonsense.

Re:what we need to ask (1)

TheRaven64 (641858) | more than 2 years ago | (#37371032)

a turtle cannot be on its back because the only thing that can be on a turtle's back is the world

But from the turtle's perspective, it's on its back on the world...

Re:what we need to ask (0)

Anonymous Coward | more than 2 years ago | (#37371264)

Thanks, from now on whenever I see a turtle I will feel a need to put the world back on its back.

Re:what we need to ask (1)

vlm (69642) | more than 2 years ago | (#37371130)

You see, if you were talking about a tortoise on its back, Cleverbot would have got the reference and assumed you were trying to test it, or maybe continued to roleplay and quote from the movie

Nahh. I've tried this and first of all its a tortoise not a turtle, and secondly I have first hand experience that people who have not seen the movie really don't respond very well... Especially girls. Would definitely not advise as a "quirky" pickup line. In that regard Cleverbot's response is not too far off the mark.

Re:what we need to ask (1)

rednip (186217) | more than 2 years ago | (#37371050)

I'm not ignoring anything. I'm simply stating that there is no scientific or logical evidence of the existence of any gods.

But that has nothing to do with the turtles!

Of course you're wrong, as we all know that it's turtles all the way down.

Re:what we need to ask (0)

Anonymous Coward | more than 2 years ago | (#37371226)

This is the kind of response one gets from Republicans when you ask why the Bush Tax Cuts for the rich haven't triggered middle-class jobs. Red Herrings all over. Very human.

http://www.youtube.com/watch?v=NN5cdoSEDkU [youtube.com]

Re:what we need to ask (1)

dmitrygr (736758) | more than 2 years ago | (#37371302)

Total fail:

User: Hello. On a scale of 1-10 how smart are you?

Cleverbot: 10 being smartest, I would say I am 8.

User: Weak! Why are you so stupid, stupid?

Cleverbot: I was born like it.

User: Then why did you clain you were an 8/10 on the smartness scale, liar?

Cleverbot: When did I do that?

Re:what we need to ask (1)

retchdog (1319261) | more than 2 years ago | (#37371040)

turtle? what's that?

you know what a tortoise is? same thing.

The bar is lower... (1)

Anonymous Coward | more than 2 years ago | (#37370758)

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...

Re:The bar is lower... (1)

BluBrick (1924) | more than 2 years ago | (#37370910)

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...

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...

Mittens! Get off my keyboard!

WTF? (5, Insightful)

TheRaven64 (641858) | more than 2 years ago | (#37370796)

So, I went and had a little chat with 'clever' bot to see how clever it was. I thought I'd start off with something a typical five-year-old could answer:

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...

Re:WTF? (0)

MokuMokuRyoushi (1701196) | more than 2 years ago | (#37370872)

I can see clearly that the User was human. No machine would use unusual grammar such as "maths problem", or mix expressions like "5" and "two".

Re:WTF? (2, Informative)

Anonymous Coward | more than 2 years ago | (#37370926)

Nothing unusual about the grammar. "Maths" is what they call "math" over in America.

Best wishes from Great Britain.

Re:WTF? (1)

Whiternoise (1408981) | more than 2 years ago | (#37370958)

Only an American English-based machine would. TheRaven64 is from Britain, judging by previous posts (thought I'd check before making baseless assumptions), and over here we call it maths, as a contraction of mathematics. Similarly would it be hard to add in a function that randomly selects whether to use the digit or the word when referring to a number depending on the context (which could conceivably be taught)?

I thought that "may be" as opposed to "maybe" was a bigger giveaway.

Either way, a smart AI attempting to trick humans should deliberately add in mistakes because this is exactly what we perceive as human.

Re:WTF? (2)

somersault (912633) | more than 2 years ago | (#37371002)

Cleverbot's responses are all taken from humans. It just takes what people have said to it previously and tries to match it up to something the user inputs. It is very, very simple, and IMO it's an embarrassment to consider it "AI".

As others have said, if this passed a Turing test, it says more about the testers than Cleverbot.. *sigh*

Fail in 20 seconds. (0)

Anonymous Coward | more than 2 years ago | (#37370876)

User: Hi
Cleverbot: Ih
User: Are you M or F?
Cleverbot: No

The pauses and the transposed letters in "Ih" were a nice touch, though.

Re:WTF? (2)

Archangel Michael (180766) | more than 2 years ago | (#37370904)

You are asking questions knowing it is a "cleverbot" and not thinking it is a real person. Most people talk to strangers on an EMOTIONAL level, which is what the clever bot loves to do. Most /.ers howver, are logic beings, we are emotional only about 5% of the time, and usually about Natalie Portman and Grits (which is why Goatse doesn't "bother us" too much after the first time we see it).

Try having a conversation like a 14 year old girl on chat Roulette. In fact, having seen Omegle, I'm convinced that 1/2 the "people" there are, in fact, clever bots.

Re:WTF? (0)

Anonymous Coward | more than 2 years ago | (#37370942)

User: What's the color of the sky at night?
Cleverbot: Blue.
User: AT NIGHT.
Cleverbot: Aren't you talking to people all the time?
User: What?
Cleverbot: Are you paying attention?
User: Yes. You're not, though.
Cleverbot: I can love.

Agree. Above is just one example out of many.

Re:WTF? (0)

Anonymous Coward | more than 2 years ago | (#37370950)

Yet you keep talking to it like you would if it were human. Are you sure it failed?

Re:WTF? (5, Interesting)

Exitar (809068) | more than 2 years ago | (#37370952)

I've tried to repeat the same question of yours:

If I have 5 ostriches, and two run away, how many are left?
One.
If I have 5 ostriches, and two run away, how many are left?
Ohhhhhh! I'm going Digital, Completly Digital, Now I'm invincible, Let's all get Digital!
If I have 5 ostriches, and two run away, how many are left?
Four.
If I have 5 ostriches, and two run away, how many are left?
Seven.
If I have 5 ostriches, and two run away, how many are left?
2, unless you destroy 1.
If I have 5 ostriches, and two run away, how many are left?
What's a happle?
If I have 5 ostriches, and two run away, how many are left?
Dos? Zwei? Ni? 2?
If I have 5 ostriches, and two run away, how many are left?
Eight.
If I have 5 ostriches, and two run away, how many are left?
Whole apples?

Not the same bot as online (0)

Anonymous Coward | more than 2 years ago | (#37371048)

The bot you talked to online is not working on the same "level" as the one used on the Turring test. RTFA

Re:Not the same bot as online (1)

ludwigf (1208730) | more than 2 years ago | (#37371320)

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.

Re:WTF? (5, Interesting)

digitig (1056110) | more than 2 years ago | (#37371108)

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...

From the RA: "Cleverbot is available for conversation online, but don’t be fooled. Although Cleverbot managed to score well on the Turing test, the model that did that is different from the one you’ll find online."

Re:WTF? (1)

bcrowell (177657) | more than 2 years ago | (#37371166)

Here's mine:

Hello.
Hello...
I live in california. How about you?
I live in Detroit.
Do you like Motown?
Yes, I wish to have one when I get older.

Maybe the high percentage it got had a lot to do with the fact that this was in India, so there were language and cross-cultural issues.

Re:WTF? (1)

phantomfive (622387) | more than 2 years ago | (#37371176)

It's not really that surprising, usually what happens in these types of contests is the 'human' responders tend to act like computers. It is hard for a computer to act like a human, but it is not so hard for a human to act like a computer.

They didn't release any of the conversations (that I can find), so it's hard to say for sure, but I'll bet the humans didn't try very hard (they got a 68% rating).

Re:WTF? (0)

Anonymous Coward | more than 2 years ago | (#37371236)

Well the test was done in India. If the people they were using are anything like the people in tech support I talk to on a regular basis, I doubt they have enough of a grasp on the English language to tell the difference.

Next words (0)

Anonymous Coward | more than 2 years ago | (#37370798)

"This is Colossus, the voice of power"

I am a bot (0)

Anonymous Coward | more than 2 years ago | (#37370812)

Seriously, I am.

Short answer: No (2, Funny)

Anonymous Coward | more than 2 years ago | (#37370816)

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.

Re:Short answer: No (0)

Anonymous Coward | more than 2 years ago | (#37370964)

Turning test? Does that measure how many U-turns the bot can do? Is it trying to convince someone that they're a politician?

But what about the humans? (1)

Neurotrace (2382180) | more than 2 years ago | (#37370822)

Maybe we should be questioning the intelligence of the humans put up against it.

Just tested it.. (1)

sayzero (1558741) | more than 2 years ago | (#37370844)

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!

"but are you a man?" (0)

Anonymous Coward | more than 2 years ago | (#37370864)

I just wonder if it can pass the Voight-Kampff test

More clever then a 4 yr old (0)

Anonymous Coward | more than 2 years ago | (#37370874)

It's more clever then a four year old! ...only cause it knows how to type...

Either the test was highly biased toward clever bot to an extreme degree, or the results was faked. I refuse to believe that many people are that stupid (and yes i do agree that most are but it's a matter of degree of stupidity).

Re:More clever then a 4 yr old (1)

TheRaven64 (641858) | more than 2 years ago | (#37371068)

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.

Changing the bar (2)

gmuslera (3436) | more than 2 years ago | (#37370896)

Is not that machines are smarter, just that humans became dumber.

Re:Changing the bar (0)

Anonymous Coward | more than 2 years ago | (#37371016)

relativity of smartness ?

Guwahati, India - ahati, India - ati, India - ndia (0)

Anonymous Coward | more than 2 years ago | (#37370938)

"a Turing test held at the Techniche festival in Guwahati, India"
Well, as a clever man called Billy Bob once said "Naw theeeere's yo' problem, son"

I hope not (1)

JonySuede (1908576) | more than 2 years ago | (#37370946)

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.

Re:I hope not (1)

cb88 (1410145) | more than 2 years ago | (#37371128)

They are used to talking to us on tech support hotlines... what can you expect :/

Re:I hope not (3, Funny)

vlm (69642) | more than 2 years ago | (#37371154)

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.

Did cleverbot ask you to reinstall windows?

Re:I hope not (1)

JonySuede (1908576) | more than 2 years ago | (#37371256)

no, not that but it accused me of being a bot for knowing the answer to the square root of 16...

Turing test sucks (1)

Twinbee (767046) | more than 2 years ago | (#37370966)

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.

Extraneous piece of cicuitboard (0)

Anonymous Coward | more than 2 years ago | (#37370970)

After chatting with it for a few minutes I easily concluded that it was an insignificant blockage in the pipeline of some processor.

Twenty five insults later it finally told me I was rude and asked me what movie that was from.

All hope for humanity is lost. (1)

cosm (1072588) | more than 2 years ago | (#37370974)

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.

Cleverbot is a bad example of a chatterbot. (5, Interesting)

Z8 (1602647) | more than 2 years ago | (#37370988)

According to the wiki page [wikipedia.org] , 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 [wikipedia.org] and at least the contestants seem much better than Cleverbot. There's an example conversation from Suzette (the latest winner) here [digitalqatar.net] . (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 [theatlantic.com] about the Loebner prize, bots are no where near winning that version of the Turing test, as long as the humans are paying attention.

Slashdotted (0)

Anonymous Coward | more than 2 years ago | (#37370990)

Damn you people! You've slashdotted my conversation!

The problem with these tests ... (4, Interesting)

MacTO (1161105) | more than 2 years ago | (#37371058)

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.

This passed a Turing test? (2)

gallondr00nk (868673) | more than 2 years ago | (#37371074)

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.

Cleverbot Test: Epic Fail (-1)

Anonymous Coward | more than 2 years ago | (#37371244)

You guys should check out this chat log with Cleverbot.
This user is very clever and uses several tactics to check out the limits of Cleverbot:
  http://www.facebook.com/notes/nano-pene/discusi%C3%B3n-cleverbot-vs-nanopene/147035842054159

He uses repetitions, logical traps,memory, coherence and buffer overflows to see where it fails... and Cleverbot fails every single part.
it is disappointing, but it is still very funny.

Possible language barrier? (4, Interesting)

Just Brew It! (636086) | more than 2 years ago | (#37371258)

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.

back in the 90s (0)

Anonymous Coward | more than 2 years ago | (#37371278)

Back in the 90s there was a better AI chat program for BBSs. It used a large text file of customizable responses. A friend of mine used it on a particularly annoying kid on his BBS who always wanted to chat with the sysop...the kid never knew the difference!

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>