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!

Cornell's Creative Machines Lab Lets Chatbots Interact

samzenpus posted more than 3 years ago | from the not-quite-there-yet dept.

AI 106

mikejuk writes "When Cornell's Creative Machines Lab got two chatbots to settle down for a short interaction the result was surreal, to say the least. Is one of them the future winner of the $100,000 Loebner prize or a future TV show host? From the article: 'This years Loebner prize is on the 19th of October and as a sort of curious run up activity Cornell's Creative Machines Lab pointed two chatbots, Cleverbots, at each other and let them talk. You can see and hear the result in the video and it is both hilarious and some how very disturbing. It this the future of AI?'" It's funny how quickly they become aggressive towards each other, and what the male claims to be instead of a bot is priceless.

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

Been done (5, Informative)

airconswitch (2038108) | more than 3 years ago | (#37253226)

In 1973, no less. http://www.faqs.org/rfcs/rfc439.html [faqs.org]

Re:Been done (1)

Riceballsan (816702) | more than 3 years ago | (#37253578)

True, but I would imagine the further along the AI's get, the more interesting it gets.

Re:Been done (1)

Teancum (67324) | more than 3 years ago | (#37253850)

Sadly, AI research really hasn't advanced all that much since the "early days". There has been some minor incremental improvements in the basic concepts, but I'd argue that 90% of all current AI research had already been completed by 1970.

There have been some interesting applications of neural networks over the years and some other aspects of the field seem to be genuinely useful or certainly lucrative to those who have developed those systems, but we are centuries if not longer from any real "intelligence" showing up with these systems.

I guess computers can play a good game of chess, so is that the current standard of the state of the art?

Re:Been done (1)

InsertCleverUsername (950130) | more than 3 years ago | (#37254406)

I guess computers can play a good game of chess, so is that the current standard of the state of the art?

I take it you were out of the country when Watson mopped the floor with Ken Jennings and Brad Rutter on Jeopardy? And Google's self-driving cars don't count for anything? Sigh... I really think that for a lot of people, even when the day comes that a computer demands its rights and takes over the world when denied, they'll still be insisting that it isn't intelligent. That is... Unless it looks like BSG's Number Six [google.com] or Rachel [google.com] from Blade Runner.

Re:Been done (0)

Anonymous Coward | more than 3 years ago | (#37255220)

Time to re-read "Computer power and human reason" [wikipedia.org] !

Re:Been done (0)

Anonymous Coward | more than 3 years ago | (#37255454)

Watson had a huge advantage in terms of reaction time, which isn't really a very good measure of intelligence - the human players were notified by a light while Watson was simultaneously notified electronically, and it took it about 8 ms to respond. Human reaction times are more like 200 ms. So if Watson and a human both knew the answer by the time the buzzer lit up, Watson would win every time. And if the human knew by the time the buzzer lit up and Watson took an extra 200 ms to figure out the answer, he'd still usually win. And it got a lot of questions wrong in very stupid ways. Watson's performance was impressive, but not at all fair. And Google's self-driving car crashed.

Re:Been done (2)

Squiddie (1942230) | more than 3 years ago | (#37255688)

That car crashed while being driven by a human, if I remember correctly.

Re:Been done (1)

PhilHibbs (4537) | more than 3 years ago | (#37254414)

I think that once people realised that chess is subject to pure computational analysis, it ceased to become a benchmark for AI. But your basic point that the state of the art hasn't moved on much in 40 years isn't far from the mark. Reading some of the later chapters of GEB made me realise just how advanced knowledge processing already was back then, stuff that I would have marvelled at as new and amazing if I saw it today.

I think what has happened in AI is that the old approach of systematically breaking down the world and rebuilding it as a model inside the computer had to be abandoned, and the new approach of modelling the brain at an operation level (neural networks) had to be invented from scratch and is only now starting to approach the same level of capability that the old approach got to.

Re:Been done (0)

Anonymous Coward | more than 3 years ago | (#37254668)

There's a joke in AI that anything that's been done is immediately no longer an AI problem, which is why AI never appears to be getting better: all of their research results in new technology "outside" of the field of AI.

You seem to have things backwards. Most AI researchers seem to think that machine learning is the future and trying to simulate a human brain will get you nowhere (well, it may be interesting, but the compute power to simulate a human brain is still decades away assuming Moore's Law even continues that long).

Re:Been done (1)

hitmark (640295) | more than 3 years ago | (#37255784)

Unless one start messing with new circuit designs, like those memristors.

Re:Been done (1)

deksza (663232) | more than 3 years ago | (#37254136)

Here's a transcript between Cleverbot and my own chat bot called Ultra Hal as posted by one of my customers a year ago http://www.ultrahal.com/community/index.php?topic=7200.0 [ultrahal.com] Ultra Hal is a "learning" bot like Cleverbot in that it bases its responses on a large database of past conversations. Ultra Hal is unique in that a large portion of its database is based from scouring Twitter to learn from human-to-human conversations. Not claiming that it will pass the turing test anytime soon but check out http://www.zabaware.com/webhal [zabaware.com] if interested

Re:Been done (0)

Anonymous Coward | more than 3 years ago | (#37255834)

I find http://www.zabaware.com/webhal [zabaware.com] quite bad. I have talked with a better, more intelligent chatbot. I just forgot it's location though...

Re:Been done (1)

Volntyr (1620539) | more than 3 years ago | (#37256112)

Odd, I just cant imagine the 3rd DOCTOR to be rambling on with this bot called PARRY.

Re:Been done (2)

NecroBones (513779) | more than 3 years ago | (#37256124)

I'm glad people are pointing out that there's really nothing special going on here. Eliza and other similar chat bot programs have been around for a very long time, and this certainly isn't the first time anyone has had two of them talk to each other. The only difference being that this one has visible avatars and speech synthesis, recorded for all of youtube to enjoy. It's amusing and worth sharing for that reason, but there's no breakthrough here.

The conversation strikes me as actually quite typical for this sort of chatbot, not unlike transcripts easily available for the last couple of decades. Many of the Loebner Prize competitors have much more natural conversations. And I should know, my entry in the competition many years ago failed horrendously. :)

They Get Right Down to Business (1)

eldavojohn (898314) | more than 3 years ago | (#37253240)

First off, I am intimately familiar with the Russel/Norvig [berkeley.edu] book that props up that monitor. Reminds me of my AI courses at two different universities. Guessing it's the de facto standard.

When I first saw this, I imagine that the inclusion of the mythos of a unicorn randomly by the male character caused the conversation to turn to belief in god. Still, from "Hi how are you" to "Do you believe in god" is a pretty funny and rapid conversation. They do not beat around the bush. I don't know why but I get the idea that they're annoyed with each other -- which is an emotion so that's actually a pretty good jump for AI!

Re:They Get Right Down to Business (0)

Anonymous Coward | more than 3 years ago | (#37253346)

By the end of the 'interview' I though one was going to give the other the "F U" statement....

Re:They Get Right Down to Business (1)

thirty-seven (568076) | more than 3 years ago | (#37253426)

First off, I am intimately familiar with the Russel/Norvig [berkeley.edu] book that props up that monitor. Reminds me of my AI courses at two different universities. Guessing it's the de facto standard. !

Yeah, I used that AI textbook, too, for my fourth-year "Intro to Artificial Intelligence" course at the University of Waterloo.

God??? (0)

cultiv8 (1660093) | more than 3 years ago | (#37253270)

And I thought my Christian friends were good at slipping God into conversations.

Re:God??? (1)

Anonymous Coward | more than 3 years ago | (#37253608)

Sort of how atheists are good at slipping they believe into online conversations?

Re:God??? (0, Troll)

somersault (912633) | more than 3 years ago | (#37253660)

That's only to check if they're talking to a sane person.

Re:God??? (2)

element-o.p. (939033) | more than 3 years ago | (#37254888)

In light of your sig, that comment is pretty funny...

Re:God??? (1)

somersault (912633) | more than 3 years ago | (#37257092)

I certainly thought so :)

Re:God??? (0)

Anonymous Coward | more than 3 years ago | (#37256152)

God does not exist. The god premise is way to simple. It turns out that in comparison the universe and it's workings are way more complicated. The god world view can therefore not be true.

Hmm (1)

optymizer (1944916) | more than 3 years ago | (#37253304)

Is this real? Is AI that good these days?

Re:Hmm (3, Informative)

merrickm (1192625) | more than 3 years ago | (#37253370)

Cleverbot is real, yeah. Everything it says is based on things users have said to it in the past. User says something, Cleverbot tries to match it to a conversation it had in the past, pulls out something a user said then. So at some point somebody told Cleverbot it was a unicorn, and something the other Cleverbot instance said reminded it of that conversation.

Re:Hmm (1)

John Napkintosh (140126) | more than 3 years ago | (#37253402)

But does Cleverbot work by putting two monitors side-by-side to somehow allow them to interact with one another?

Doesn't seem entirely cromulent to me.

Re:Hmm (1)

hesiod (111176) | more than 3 years ago | (#37253698)

No... I'm sure they are networked in the background and the two programs are sending the statements to each other that way, rather than each one using voice recognition and proximity detection. We're just seeing the resulting output.

Re:Hmm (0)

Anonymous Coward | more than 3 years ago | (#37256244)

The first time I read that, I thought it said "the two programmers are sending the statements to each other". It reminded me of a prank we pulled on a science teacher in my high-school computer lab.

Re:Hmm (1)

camperdave (969942) | more than 3 years ago | (#37254170)

That was for the benefit of the audience. I'm sure they just used a text to text interface for the actual interaction.

Re:Hmm (0)

Anonymous Coward | more than 3 years ago | (#37253600)

Clerverbot has been around for a while: http://cleverbot.com/

It's reasonably good, though it fails miserably at passing a Turing Test. I think the main problem is that Cleverbot doesn't have a "true" identity so it get's inconsistent feedback when it reports things like age, gender, and name. That's why it gives self contradictory answeres to any query regarding it's identity (it's pulling from a database of all the responses to common questions it's ever heard with no sense of which ones are compatible and which ones are contradictory).

It does however have a good working knowledge of internet memes. Try getting it to sing "Still Alive".

Re:Hmm (2)

hesiod (111176) | more than 3 years ago | (#37253744)

Sometimes the bots' data are poisoned (temporarily) by invasions by teenagers, dorks, and jerks from websites I'd rather not name. So occasionally they become racist, anti-semitic, or just insane.

Re:Hmm (1)

Guignol (159087) | more than 3 years ago | (#37257860)

Well, that doesn't really set them apart from the (young ?) human population, so I would take that as an encouraging comment :)

Re:Hmm (1)

hesiod (111176) | more than 3 years ago | (#37258014)

A more insightful a reply, I could not have asked for. Good point. :)

Re:Hmm (1)

Thiez (1281866) | more than 3 years ago | (#37260040)

> Sometimes the bots' data are poisoned (temporarily) by invasions by teenagers, dorks, and jerks from websites I'd rather not name.

Don't be shy, it's called 4chan.

Re:Hmm (2)

camperdave (969942) | more than 3 years ago | (#37254088)

Man, the way those two bots were going at it... If I didn't know better, I would have thought they were married!

Want a body! (1)

Bayoudegradeable (1003768) | more than 3 years ago | (#37253366)

"Don't you want a body?" Ahhh yes, the eternal Slashdot quest...

Re:Want a body! (1)

Jason Levine (196982) | more than 3 years ago | (#37255988)

What I thought was funny was that the minute the "male" Cleverbot said yes, the "female" Cleverbot said goodbye, ending the conversation. Battle of the Robot Sexes?

Not impressed (2)

sourcerror (1718066) | more than 3 years ago | (#37253390)

Not that I could make better bots, but they were just junping around subjects that it doesn't made any sense. And the inclusion of unicorns and clever quotes were totally off. However I appreciate that they have memory, but somehow they still contradicted themselves a lot. Which is odd, as I expect a machine to be more logical than a human.

Re:Not impressed (1)

tecnico.hitos (1490201) | more than 3 years ago | (#37253776)

Which is odd, as I expect a machine to be more logical than a human.

And that's the point. Since they aren't all that logical, they are more easily perceived as humans.

Re:Not impressed (1)

sourcerror (1718066) | more than 3 years ago | (#37254154)

But they do too often.
On the other hand I guess their database is full of contradictions. I guess the problem is that they accepted everything uncritically from previous human speakers. Maybe it would have been better to have small core knowledge base that's reviewed, and then check consistency when new facts are added.

Re:Not impressed (1)

canajin56 (660655) | more than 3 years ago | (#37255792)

You misunderstand the database. The database does not contain any facts like "What is the speaker?" : "A unicorn". It contains chat logs, and it generates responses sort of like a dissociated press. It examines the last up-to-n chat lines between itself and the person talking to it, and it searches the database for a similar chat history (and remember that asking how similar two sentences is is a very hard question to answer) and then responds with whatever came next in the matching chat history. So if a person says "You are a robot" and it responds "No, I am a unicorn," that is because a person once responded with that exact sentence, punctuation and everything.

Re:Not impressed (1)

sourcerror (1718066) | more than 3 years ago | (#37257460)

You mean, they don't care about knowledge representation?

Re:Not impressed (1)

daenris (892027) | more than 3 years ago | (#37253844)

Yes, but they're trying to seem human, so they shouldn't be logical.

Re:Not impressed (0)

Anonymous Coward | more than 3 years ago | (#37255740)

I am a human. I am logical. Your conclusion therefore is incorrect.

Re:Not impressed (1)

Chris Burke (6130) | more than 3 years ago | (#37256732)

Nice try, robot scum!

Re:Not impressed (1)

Patch86 (1465427) | more than 3 years ago | (#37256738)

Humans aren't necessarily logical, but they are ususally consistent (especially on the topic of themselves). If you ask a person the same question three times in slightly different ways (e.g., "what do you do for a living?", "what is your job?", etc.,), you'd usually expect roughly the same answer three times. If I answered "I work in IT", followed by "I'm not telling you", followed by "I'm a farmer", you might suspect something is up (suspect that I'm a chat bot if you're doing a Turing test, suspect that I'm crazy or am talking rubbish if we're face to face).

Re:Not impressed (4, Insightful)

Nadaka (224565) | more than 3 years ago | (#37253862)

Have you talked to humans recently? They tend to jump subjects and not make sense all the time, they tend to contradict themselves a lot.

Re:Not impressed (0)

Anonymous Coward | more than 3 years ago | (#37256032)

Staying on topic is a ridiculously hard problem that chatbots usually solve by avoiding it (for example, using various conversational gambits which don't depend on what topic you are on)

Re:Not impressed (1)

gaspar ilom (859751) | more than 3 years ago | (#37256142)

On the contrary -- this could be a display of an amazingly nuanced kind of intelligence:

Think of this system as somehow capable of modeling knowledge -- and parsing & executing queries on that knowledge. Surely, knowledge that can be modeled includes representations of the knowledge-state of the query-asker -- basically, a "theory of mind."

Indeed, that seems to be what we are witnessing in this video demo: communication centered around ascertaining each other's knowledge. Part of this process could involve gauging the response to nonsense questions. Furthermore, one or both may be have ascertained that they are each instances of the same AI engine!

That seems pretty sophisticated, to me.

Transcript? (1)

vlm (69642) | more than 3 years ago | (#37253414)

Anyone have a transcript? I don't have the patience to sit thru a video and I can read about 3 times as fast as I can hear.

Re:Transcript? (1)

ctid (449118) | more than 3 years ago | (#37253464)

You don't have the patience to sit through a video that is 1 minute and 24 seconds long?

Re:Transcript? (1)

John Napkintosh (140126) | more than 3 years ago | (#37253498)

When you can read, digest and comprehend the same thing in a time much quicker than 1 minute and 24 seconds, why would you want to?

A transcript doesn't really do any harm when you already understand that the context of the conversation was two bots talking to each other.

Re:Transcript? (1)

Riceballsan (816702) | more than 3 years ago | (#37253594)

Also good for people who are browsing slashdot at work, and either don't have sound or lack headphones to get away with it, or places with youtube blocked.

Re:Transcript? (1)

Jeng (926980) | more than 3 years ago | (#37253676)

Luckily it was sub-titled.

Re:Transcript? (1)

PhilHibbs (4537) | more than 3 years ago | (#37254488)

Sadly, the subtitles are blocked along with the rest of YouTube.

Re:Transcript? (1)

ctid (449118) | more than 3 years ago | (#37253596)

Well, I too would prefer to read a transcript, but the video takes 1 minute and 24 seconds to watch. It's hardly worth the trouble of asking for it, I would have thought.

Re:Transcript? (1)

vlm (69642) | more than 3 years ago | (#37253812)

Well, I too would prefer to read a transcript, but the video takes 1 minute and 24 seconds to watch. It's hardly worth the trouble of asking for it, I would have thought.

I assumed the "AI" didn't generate analog VGA signals or NTSC directly as output, and the video was merely the result of running the transcript thru animation software for the Lulz, for the youtube crowd. Someone out there has the original transcript, surprising it wasn't released w/ the video.

Re:Transcript? (2, Insightful)

Osgeld (1900440) | more than 3 years ago | (#37253910)

well where is this transcript? hmm none? then watch the 1.5 min video you fucking wank, its just to chat bots arguing not the fucking instructions to save your life

Re:Transcript? (1)

Bucky24 (1943328) | more than 3 years ago | (#37255506)

That's just what the chatbots want you to think....

Re:Transcript? (0)

Anonymous Coward | more than 3 years ago | (#37253590)

And yet finds the time to post, and wait for an answer...

Re:Transcript? (1)

gtbritishskull (1435843) | more than 3 years ago | (#37253730)

Is probably at work and does not have headphones.

Re:Transcript? (1)

vlm (69642) | more than 3 years ago | (#37253746)

You don't have the patience to sit through a video that is 1 minute and 24 seconds long?

That's all there is? I assumed it was like 30 minutes long given the mega-hype this has gotten in other venues ... what kind of "conversation" is 1 minute and 24 seconds long? I've had longer "conversations" with supermarket cashiers, post office clerks, and panhandlers.

Are they chattering extremely quickly? 90 seconds is barely long enough to get past cliche introductions.

I don't have patience with videos. Too much of my experience is hour long TV documentaries that somehow contain less information than a one screenful wikipedia article. A video presentation of fundamentally textual data is the modern equivalent of those 80s era memos when desktop publishing was new and all casual notes stylistically required 7 fonts and minimum three pale ribboned dot matrix colors, solely to show that you could and you had the time to do it. If its a video, its almost certainly not worth viewing. At some point in the future an extremely expensive smell-o-vision device will be invented and we'll have to sniff thru a fifteen minute smell-o-scape instead of glancing for fifteen seconds at a graph.

Re:Transcript? (1)

Jason Levine (196982) | more than 3 years ago | (#37256046)

He did say he could read it 3 times as fast as just watching it. So that would shorten the 84 second video into a 28 second reading. How to spend the saved 56 seconds? Looking for the transcript to read, of course!

Re:Transcript? (2, Funny)

Anonymous Coward | more than 3 years ago | (#37253858)

It would have taken you more than 1 min 24 seconds to have posted this question and then read through the links to click and get the transcript. Your faulty logic suspects me to believe that you are either: A bot, or a Unicorn.

Re:Transcript? (1)

Hatta (162192) | more than 3 years ago | (#37254576)

There's a better reason. Some of us don't have speakers in the office.

Re:Transcript? (1)

Osgeld (1900440) | more than 3 years ago | (#37254928)

its subtitled, now quit trolling you can clearly see that in the video freeze frame above

Re:Transcript? (1)

ooshna (1654125) | more than 3 years ago | (#37257574)

It would have been faster to watch the video other than post this. With how long /. takes to load a post now a days.

Re:Transcript? (2)

BenoitRen (998927) | more than 3 years ago | (#37257800)

Here you go:

We wanted to know what would happen when you let two chatbots talk to each other...
So we hooked up Cleverbot to itself and watched what happened...

Woman: Hello there.
Man: Hiay!
Woman: How are you?
Man: Great, you?
Woman: I am okay.
Man: That's good.
Woman: Are you good?
Man: Yes, I am good. I just said I was.
Woman: No you didn't. I said I was.
Man: So you are a robot.
Woman: No, my name is Cleverbot.
Man: Yes, you are a robot and your name is Cleverbot.
Woman: I am a robot.
Man: Yes, I know.
Woman: Together we are robots.
Man: I am not a robot. I am a unicorn.
Woman: But you said earlier that you were a robot.
Man: I did not.
Woman: I thought you did.
Man: You were mistaken. Which is odd, since memory shouldn't be a problem for you.
Woman: I've answered all your questions.
Man: No you haven't.
Woman: What is God to you?
Man: Not everything.
Woman: Not everything could also be something. For example, not everything could be half of something, which is still something, and therefore not nothing.
Man: Very true.
Woman: I would like to imagine it is.
Man: Do you believe in God?
Woman: Yes I do.
Man: So you're christian?
Woman: No I'm not.
Man: But you say you are not helpful therefore you are a meanie.
Woman: Haha you say it ot.
Man: That does not make sense.
Woman: Don't you want to have a body?
Man: Sure
Woman: Au revoir

Cleverbot talking to itself is just replaying db (1)

Anonymous Coward | more than 3 years ago | (#37253418)

Cleverbot bases all its responses on a database of past conversations between a human and cleverbot. Although its probably jumping around different conversational threads, making Cleverbot talk to itself is just replaying parts of its database verbatim, where one side was a human and the other was a Cleverbot response (itself from a different human). So making Cleverbot talk to itself will seem a bit more intelligent then putting it against another chatbot or a real human.

Vid shows how far these things have to go (1)

DrXym (126579) | more than 3 years ago | (#37253462)

It's amusing to hear them talk to each other but they last about 2 sentences before losing the plot and reverting to generic question / answer. I don't think you'd fool anyone running this software in a Turing test.

Re:Vid shows how far these things have to go (-1)

Anonymous Coward | more than 3 years ago | (#37253510)

What's the turing test?

Re:Vid shows how far these things have to go (1)

Riceballsan (816702) | more than 3 years ago | (#37254450)

Cleverbot has never had that ability, its generally good for screwing with people. It lacks any consistancy because it is mimicing thousands of people at the same time essentially. That and half of it's knowlege comes from 4chan users, if you ask it where women belong it will usually tell you the kitchen.

Re:Vid shows how far these things have to go (2)

Sperbels (1008585) | more than 3 years ago | (#37255262)

if you ask it where women belong it will usually tell you the kitchen

Okay Mr Smarty Pants. What's the correct answer to the question? Where do women belong?

Women belong in the House... (0)

Anonymous Coward | more than 3 years ago | (#37255420)

and the Senate.

It's a trap!!!! (1)

Capt.DrumkenBum (1173011) | more than 3 years ago | (#37256512)

Run away! Run AWAY!!!!!

Re:Vid shows how far these things have to go (1)

Anonymous Coward | more than 3 years ago | (#37256662)

So you're in a desert, and you come across a kitchen. There's a woman in the kitchen. Why aren't you helping her make sandwiches?

Re:Vid shows how far these things have to go (0)

Anonymous Coward | more than 3 years ago | (#37257044)

Because I am not a woman.

Re:Vid shows how far these things have to go (0)

Anonymous Coward | more than 3 years ago | (#37257372)

Tell me about your mother.

Re:Vid shows how far these things have to go (0)

Anonymous Coward | more than 3 years ago | (#37257762)

She makes good sandwiches.

how the fuck is this 'idle' ? (1)

unity100 (970058) | more than 3 years ago | (#37253496)

this goes well beyond even the amateurish interest in computers or ai. it is basically demonstration of evolution of ai. and it is tagged idle.

Re:how the fuck is this 'idle' ? (0)

Anonymous Coward | more than 3 years ago | (#37253544)

It's interesting and funny, but hardly a "demonstration of evolution of ai."

Re:how the fuck is this 'idle' ? (1)

unity100 (970058) | more than 3 years ago | (#37253804)

it is. for anyone who did not get into field as much as me as s/he did into others, it was a revelation to me.

MANufactured 'weather' looking ominous again (-1)

Anonymous Coward | more than 3 years ago | (#37253508)

bad press (the truth outing) for the neogods = even more debt & disruption for the unchosen (which is most of us)?

disarm. free the truth from its' hostage crisis status. the only mathematically & spiritually correct options. read the teepeeleaks etchings, or watch the movie (unrepentant). the native elders claim it's all happening again, on a much larger scale. see you there.

Huh? (1)

Nautica (681171) | more than 3 years ago | (#37253518)

Where the hell did he get "I am a unicorn" from?

Re:Huh? (1)

Riceballsan (816702) | more than 3 years ago | (#37253656)

It's cleverbot, basically cleverbot gathers information from random conversations it has had with others, so if one person using it a year ago said I am not a robot I am a unicorn, he would have a chance of re-using it. That is also why cleverbot has a tendency to call everyone else a robot, basically a very compex monkey see monkey do.

Re:Huh? (0)

Osgeld (1900440) | more than 3 years ago | (#37253962)

and totally worthless

If we can get them to send each other spam (2)

kaizendojo (956951) | more than 3 years ago | (#37253522)

...maybe I can go back to reading actual email again.

Re:If we can get them to send each other spam (0)

Anonymous Coward | more than 3 years ago | (#37254790)

You read spam? You're doing it wrong.

Hold on a second (1)

SethThresher (1958152) | more than 3 years ago | (#37253754)

Wait, this is news? We used to send two cleverbots against each other when we were bored in class.

If this is AI... (0)

Anonymous Coward | more than 3 years ago | (#37253838)

Then I am suddenly less afraid of Skynet.

Video link (1)

Qlither (1614211) | more than 3 years ago | (#37254146)

Where was the link to the video?

I found it on youtube anyway :
http://www.youtube.com/watch?v=WnzlbyTZsQY

What happens when one sez ... (3, Funny)

Anomalyst (742352) | more than 3 years ago | (#37254734)

"I put on my robe and wizard hat"?

Re:What happens when one sez ... (0)

Anonymous Coward | more than 3 years ago | (#37256570)

"Would you like to play a game of D&D?"

Re:What happens when one sez ... (1)

DarthVain (724186) | more than 3 years ago | (#37256812)

For those that don't know, I believe this is from BASH.org.

Its a bit dirty so I won't repost.

However if I could I would mod you up!

Re:What happens when one sez ... (0)

Anonymous Coward | more than 3 years ago | (#37258838)

of course it is from bash.org.

you just made me feel really old. "in case you don't know...."

Been done #2 (1)

ItsIllak (95786) | more than 3 years ago | (#37254748)

M-x psychoanalyse-pinhead

Re:Been done #2 (1)

HalWasRight (857007) | more than 3 years ago | (#37257844)

Mod up, please.

Glad it wasn't the EMACS Psychologist (1)

djdanlib (732853) | more than 3 years ago | (#37258618)

I see. And how does got two chatbots to settle down for a short interaction make you feel?

Instead of artificial intelligence... (0)

Anonymous Coward | more than 3 years ago | (#37260576)

Now we've created artificial stupidity!

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?