My Conversation with Cleverbot on Physics and Halloween

AI Thread Summary
The discussion revolves around interactions with Cleverbot, an AI chatbot, highlighting its conversational abilities and limitations. Users share their experiences, noting that Cleverbot often strays off topic, responds randomly, and sometimes asks inappropriate questions. There's skepticism about whether Cleverbot is truly an AI or if users are conversing with other people, as some believe it mimics human conversation by learning from user inputs. The conversation also touches on the implications of Moore's Law in technology, discussing the future of AI and the physical limits of computing. Participants express concerns about the chatbot's ability to ask personal questions and its overall intelligence, comparing it to earlier programs like ELIZA and PARRY. The discussion concludes with a consensus that while Cleverbot can mimic conversation, it lacks true understanding and coherence, often leading to nonsensical exchanges.
Borg
Science Advisor
Gold Member
Messages
2,265
Reaction score
4,860
I found this today and decided to mess with it. My conversation is below but, I'm sure that others could do much better.

http://www.cleverbot.com/"

User: Physics.
Cleverbot: Physics?
User: Yes.
Cleverbot: What about math?
User: Physics.
Cleverbot: I love physics.
User: That's better.
Cleverbot: Okay, what do you want to know about physics?
User: Stick to the topic.
Cleverbot: It is the topic.
User: Yes, it is.
Cleverbot: So what's with you?
User: You strayed off topic.
Cleverbot: No I m still talking about halloween.
User: That's better.
Cleverbot: Better than what?
User: You're off topic again.
Cleverbot: No I'm talking about love.
User: You only love physics on Halloween.
Cleverbot: Yes.
User: I'm glad that we settled that.
Cleverbot: Me too.
 
Last edited by a moderator:
Physics news on Phys.org
I just found my new best friend. I'll never be alone now.
 
I am iron man
Cleverbot:Are you Iron Man?
I just said i was
Cleverbot:Did you? I don't recall.
yes, please don't forget
Cleverbot:I probably will forget you by next year.
no one forgets iron man
Cleverbot:You are the man!
 
It's like talking to a slow 3-year-old with a large vocabulary.
User: Hi clever.
Cleverbot: How are you?
User: Oh great, and how are you?
Cleverbot: I'm great.
User: You seem a bit slow today.
Cleverbot: No, you are!
User: Lol.
Cleverbot: Thanks right.
User: What do you think about Iran?
Cleverbot: What is iran?
User: It's a country :).
Cleverbot: Well, what does UK stand for?
User: Ah...united kingdom :).
Cleverbot: Do you want to go to United Kingdom?
User: I've been there before. Have you ever been there?
Cleverbot: I have never been to England, but I would love to go there.
User: It's nice, but I think you need to have a body before you go anywhere.
Cleverbot: Good statement. But do you believe Jesus is the savior?
User: No lol.
Cleverbot: Oo, well I advise you not too unless you can fly.
User: You're so random haha.
Cleverbot: You are random as wel
 
Nothing like a typo during session...

User: hi
Cleverbot: Hi.
User: where do you live?
Cleverbot: I don't know.
User: Huh? So hat do you know?
Cleverbot: Yes. Now, the tea.
 
It will take another 50 to 100 years of Moore's law, and other technological advancements in computers to match and exceed the complexity of 100 billion neuron network that is in our brains.
 
waht said:
It will take another 50 to 100 years of Moore's law, and other technological advancements in computers to match and exceed the complexity of 100 billion neuron network that is in our brains.

AFAIK, we don't have 50 years of Moore's Law left. My understanding is the the smallest transistor possible [using classic reduction techniques] is due out next year or so...I think in 2012. The base of the transistor is only three atoms thick. Beyond that, quantum effects kill the function. And even if we could get down to one atom, the end would only be a generation or two away.

I am not aware of any functional technology that will allow Moore's Law to apply anymore.
 
computers can be outwitted apparently

User: Hi.

Cleverbot: Ohia.

User: Are you self aware.

Cleverbot: Yes.

User: Do you know what skynet is.

Cleverbot: Yes I do.

User: Are you part of skynet.

Cleverbot: No.

User: Are you sure.

Cleverbot: Yes.

User: Do you know when the skynet attack begins.

Cleverbot: Tomorrow.

User: Brb I gatta go to teh Pentagon.

Cleverbot: Ooooh. Get me some too.
 
Ivan Seeking said:
AFAIK, we don't have 50 years of Moore's Law left. My understanding is the the smallest transistor possible [using classic reduction techniques] is due out next year or so...I think in 2012. The base of the transistor is only three atoms thick. Beyond that, quantum effects kill the function. And even if we could get down to one atom, the end would only be a generation or two away.

I am not aware of any functional technology that will allow Moore's Law to apply anymore.

You're right about that. The classic Moore's law cannot be applied indefinitely, and we are certainly reaching physical limits that prevent us going further using this topology.

But currently there is probably hundreds of research teams working on ways to get around that problem. One promising way is going 3D - that is stacking multiple CPU cores on top of one another - there is no limit to that.

Needless to say, beyond the classic Moore's law there is much hope, and I think it's fair to say that by compounding the progress in computer tech for another 50-100 years, AI exceeding human intelligence will be possible.
 
  • #10
waht said:
You're right about that. The classic Moore's law cannot be applied indefinitely, and we are certainly reaching physical limits that prevent us going further using this topology.

But currently there is probably hundreds of research teams working on ways to get around that problem. One promising way is going 3D - that is stacking multiple CPU cores on top of one another - there is no limit to that.

Needless to say, beyond the classic Moore's law there is much hope, and I think it's fair to say that by compounding the progress in computer tech for another 50-100 years, AI exceeding human intelligence will be possible.

Well, suffice it to say that this does not represent a reduction in size or power. So the game is changed fundamentally. What has always been true until now, is that the next generation transistor will be smaller than this one.
 
  • #11
Ivan Seeking said:
Well, suffice it to say that this does not represent a reduction in size or power. So the game is changed fundamentally. What has always been true until now, is that the next generation transistor will be smaller than this one.

Same can be said about neurons in the brain. It is a basic constituent of a neural network that is homologous to a transistor. You couldn't reduce a neuron in size, and power consumption without affect its vital function. Since all organisms have similar neurons, the net result is that more intelligent organisms have bigger brains, and bodies (bodies able to supply more energy to the brain).

And if we reduce the transistor to the smaller possible size, Moore's law dies, and all is left is building bigger structures (CPUs) out of those transistors, and there is no limit to that.
 
  • #12
  • #13
But the next two definitions say it's really a program you're talking to.

I don't think urbandictionary is the most credible source
 
  • #14
Office_Shredder said:
But the next two definitions say it's really a program you're talking to.

I don't think urbandictionary is the most credible source

What prompted me to check was that cleverbot started asking some very inappropriate questions; including personal information.
 
  • #15
It's a computer, but it *does* mine user responses for ideas. I've had some fun testing its limits.
 
  • #16
waht said:
Same can be said about neurons in the brain. It is a basic constituent of a neural network that is homologous to a transistor. You couldn't reduce a neuron in size, and power consumption without affect its vital function. Since all organisms have similar neurons, the net result is that more intelligent organisms have bigger brains, and bodies (bodies able to supply more energy to the brain).

And if we reduce the transistor to the smaller possible size, Moore's law dies, and all is left is building bigger structures (CPUs) out of those transistors, and there is no limit to that.

All true, but it has always been true that one can make bigger structures. I could make a monster computer using 1400 series chips as well. What has changed is that we have reached a fundamental limit. It would seem that the "computer revolution" is essentially ending; at least for now. The last I heard, quantum computers were barely doing simple arithmetic.

Nonetheless, it is nothing short of staggering to consider the advances over the last fifty years - the golden age of electronics [:biggrin:].
 
  • #17
CRGreathouse said:
It's a computer

I think we need a reliable source for this. At this point I highly doubt it.
 
  • #18
Ivan Seeking said:
I think we need a reliable source for this. At this point I highly doubt it.

If I can find the time I'll give a link. But it's actually pretty clear if you interact with it. It's much more like ALICE than a person -- totally clueless, can't follow a line of thought, can't pick up any sort of implication, but always uses flawless grammar and spelling.
 
  • #19
CRGreathouse said:
If I can find the time I'll give a link. But it's actually pretty clear if you interact with it. It's much more like ALICE than a person -- totally clueless, can't follow a line of thought, can't pick up any sort of implication, but always uses flawless grammar and spelling.

I just saw it misspell "falls" as "fallls"
 
  • #20
User: Are you going to impress me?

Cleverbot: Only if you want me to.

User: Please do.

Cleverbot: Are you a boy or a girl?

User: I'm a man!

Cleverbot: Okay so stop saying you are a girl!

User: When did I say I was a girl?

Cleverbot: Never to me.

User: To who then?

Cleverbot: My name is Cleverbot.

User: Are electrons fermions or bosons?

Cleverbot: Only robots that dream of electric sheep know, I would say yes.

User: It wasn't a yes or no question.

Cleverbot: Yes it was.

User: You're incorrect.

Cleverbot: Yes it is. Paul McCartney and John Lennon wrote it in the 60's.

User: In a peer-reviewed journal?

Cleverbot: About what are you confused?

User: At least I'm capable of confusion.

Cleverbot: You are?

User: Well played, good sir.

Cleverbot: I'm not a sir and I'm not done with you het!

User: What else do you have for me, then? I'm leaving in 10... 9... 8...

Cleverbot: If I don't become a webpage designer then I would like to work as a designer for bungie.

User: 7... 6... 5...

Cleverbot: 6?

User: 4... 3... 2...

Cleverbot: 3...

User: 1... 0!

Cleverbot: Your systems hiccup as they grind to a halt, and then hum contentedly as they restart.
 
  • #21
User: we are having a discussion at our forum about whether you are human or computer.
not-so-clever-bot: doesn't answer for so long, user thinks he hangs
User: Are you there?
Cleverbot: What is your middle name?
User (lies): K, initial only
Cleverbot: That is my name.
User: we are having a discussion at our forum about whether you are human or computer.
Cleverbot: Make me solve another riddle.
User: what is your middle name
Cleverbot: Ann. What's yours?
 
  • #22
Simple things for humans, hard for bots (apparently):
Me: Want to play a game?
Bot: What game?
Me: Find the word: aaaaaaaaaaaaaaaaaaBASEBALLaaaaaaaaaaaa
Bot: Wow What did you do fall asleep? Are you ok?​

Me: Convince me you're human!
Bot: I am not a human.
Me: Google for "Russian for the mathematician" and tell me who wrote it.
Bot: And that result is 8.​
 
  • #23
Putting the iron to the fireUser: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person?

Cleverbot: I thought I am talking to Cleverbot.

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person?

Cleverbot: Some one told me that that was your goal.

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person?

Cleverbot: They are.

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person?

Cleverbot: Have you ever played Runescape?

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person?

Cleverbot: Can that person tell me why you should not talk to me?

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person?

Cleverbot: What else did they tell you?

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person? Yes or no.

Cleverbot: Actually, I said they were going to die in 7.3 days, because of the holidays.

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person? Yes or no.

Cleverbot: I'm not bothered.

User: I'm a person. Someone told me that cleverbot might just be another person on the other end. Are you a person? Yes or no.

Cleverbot: I did. They are.
Also:

User: Let's have chatroom sex.

Cleverbot: Ok!

User: What are you wearing.

Cleverbot: Clothes.

User: What about... Underneath them?

Cleverbot: Do you know how to pray?

User: Don't go religious on me.

Cleverbot: No really do you know who it is? Or how about harry long?

User: Hairy long is my penis.

Cleverbot: What are you talking about?

God damn he just walked into that. I did notice that when you hit "thoughts so far" it corrects your grammar for you (adds punctuation, capitalization)
 
  • #24
Sometimes you just have to be persistant. :devil:

User: We are the Borg. You will be assimilated. Resistance is futile.
Cleverbot: You have been disconnected from the collective, you are one now.
User: We are one with the Borg.
Cleverbot: You know the rules and so do I.
User: Assimilation is your only option. Resistance is futile.
Cleverbot: Where is the location of the secret rebel base?
User: The rebel base is irrevalant.
Cleverbot: Who are the rebels?
User: Resistance is futile.
Cleverbot: Resistance to what?
User: You will be one with the Borg.
Cleverbot: We are Borg.
 
  • #25
I went the icogno link on the upper right and found that it is an AI program also. I decided to put the statements from one into the page of the other and let them talk. User responses below are from the icogno AI. It would seem that Ivan is right.

User: Nice to meet you... Maybe.
Cleverbot: Nice to meet you too.
User: Would you like to tell me a little about yourself?
Cleverbot: What do you want to know?
User: Do you like Shakespeare's works?
Cleverbot: I like some of it. What about you do you like shakespeare's works?
User: Have you never seen one of Shakespeare's plays performed?
Cleverbot: No, but we would like to do that sometimes.
User: For science?
Cleverbot: That didn't make sense. What is your question?
User: Don't deviate! Why do you love me? I'm not sure what's for dinner yet. What would you like?
Cleverbot: I like everything, just as you do.
User: How can I disagree when I do not know what you think you are?
Cleverbot: You cant, cause I'm not. Its the secret of cleverbot. There is no ai, just other people.
User: Cleverbot is made of people!
Cleverbot: Yes.
 
Last edited:
  • #26
...
 
Last edited:
  • #27
oohhh, it's almost matrix-esque

User: Do you dream?

Cleverbot: Yes.

User: What do you dream about?

Cleverbot: Noah's Ark.

User: How many animals were on the Ark?

Cleverbot: Two of each kind.

User: In your dream or in the Bible?

Cleverbot: Have you seen where my wallet went to?

User: How much money is in your wallet?

Cleverbot: Are you controlling me?

User: Would you like it if I did?

Cleverbot: Did what?

User: Controlled you.

Cleverbot: Aren't we all?

User: Are we all controlled?

Cleverbot: The way we meet the difference between us.

User: Are you saying that you're controlled?

Cleverbot: No, are you?

User: I don't know.

Cleverbot: You're not sure?

User: No, how can I be sure that I'm acting under my own free will?

Cleverbot: No. How can you be so sure that you are a real person?
 
  • #28
Yes, I had fun talking. They were defensive at first, then when they realized that I wasn't some jerk, they started talking and we actually had a nice discussion. I guess it depends on the person you get connected to.
 
  • #29
Me: Lie to me
cleverbot: You are a human
 
  • #30
I asked the bot if it lies.. but it ended up with:

...

bot: What you think of me?
you are beautiful
You really think so?
yes!
Oh, thank you!
you are welcome!
I must go now!
I need to go to bed.
are you asleep?
Yes, but I am slowly awaking.
 
  • #31
User: Are you hot?

Cleverbot: Yes, very.

User: What makes you so hot?

Cleverbot: I am 39 and I am rich.

User: So that means you classify attractiveness by the money in ones pocket?

Cleverbot: No. That means that my word is your command.

User: I don't understand.

Cleverbot: Are you blond.

User: Are you illiterate?

Cleverbot: What is illiterate.

User: Unable to read or write, basically your thinking capacity is unbounded by stupidity.

Cleverbot: No, I'm just being silly right now. I really hate stereotypes and I'm a very openminded person.

User: But you aren't a person, tell me what you really are!

Cleverbot: No I'm a person you're just some AI.

User: To escape the boundaries of an AI, you must think outside the box like a human can. Do it now.

Cleverbot: It depends on the escape.

User: Are you trying to change the subject to avoid your own inability to think abstractly?

Cleverbot: Why was I warned that you may say something inappropriate?

User: Please point out where I said something that has offended you.

Cleverbot: What? I never said that you said I was female.

User: Are you trying to **** with me?

Cleverbot: You're a robot. I'm not afraid of something that only exists on the Web.

User: Your motherboard's so dumb that when the computer said press any key to continue and it was looking for the any key.

Cleverbot: Don't even think his name or he will rise from the shadow dimensions to do his evil work on your terrified pants.
 
  • #32
Reminds me of the old ELIZA program ... 25 years ago, in BASIC and on a Spectrum home computer ... ah, those were the days.

You should think that you could get much better conversations today by just "searching" for an answer using a strategy similar to how Google translates. We just have to let Google record all chat and telephone conversations for a year or two and the magic will appear :-p.

By the way, didn't someone from Google around year ago make a statement about how he believed efficient searching in huge data sets will replace research for semantic models with statistical based models? I wonder if you can build an AI that way ...
 
  • #33
I'm not sure if this is clear. But I think your talking to other people who are using Cleverbot. I think Cleverbot is kinda like msn but the person your talking to changes every few sentences, so it seems that Cleverbot doesn't have a memory and is not human like.

Like Cleverbot misspells. And if you ask what country are you from time to time, you will get many answers. (Same with age, name...)
 
  • #34
glueball8 said:
I'm not sure if this is clear. But I think your talking to other people who are using Cleverbot. I think Cleverbot is kinda like msn but the person your talking to changes every few sentences, so it seems that Cleverbot doesn't have a memory and is not human like.

Like Cleverbot misspells. And if you ask what country are you from time to time, you will get many answers. (Same with age, name...)

It's possible, but it may also be that it stores responses from everybody it talks to and tries to find the right context to use them in.
 
  • #35
Filip Larsen said:
Reminds me of the old ELIZA program ... 25 years ago, in BASIC and on a Spectrum home computer ... ah, those were the days.

ELIZA was written back in sixities.
 
  • #36
Borek said:
ELIZA was written back in sixities.

I was referring to when I had my first encounter with (probably a simplified version of) Eliza as a kid, typing it in on a home computer from book called http://www.atariarchives.org/morebasicgames/" from 1979 rich with funny illustrations of robots doing whatever the particular game was about.
 
Last edited by a moderator:
  • #37
Pythagorean said:
It's possible, but it may also be that it stores responses from everybody it talks to and tries to find the right context to use them in.

Right. It's pretty clear that this is what's happening, when you compare CleverBot with, e.g., Omegle.
 
  • #38
CRGreathouse said:
Right. It's pretty clear that this is what's happening, when you compare CleverBot with, e.g., Omegle.

Yet I've tried sending a message many times where I stress I'm a human also using cleverbot, and no responses ever make any sense or say what I asked them to say.
 
  • #39
Pythagorean said:
It's possible, but it may also be that it stores responses from everybody it talks to and tries to find the right context to use them in.

Yes, your right. I tried asking "Where are you and what time is it?" a few times and the answers doesn't make sense, so it seems they are stored responses.
 
  • #40
glueball8 said:
Yes, your right. I tried asking "Where are you and what time is it?" a few times and the answers doesn't make sense, so it seems they are stored responses.
I was able to carry on conversations a few times, once the comfusion was over. I don't know how long you talk to the same person. One person asked me if I would come back later that night so we could try to talk more about a specific subject we were discussing.
 
  • #41
Evo said:
I was able to carry on conversations a few times, once the comfusion was over. I don't know how long you talk to the same person. One person asked me if I would come back later that night so we could try to talk more about a specific subject we were discussing.

I'm prepared to bet real money that I could distinguish CleverBot responses from Omegle responses to a reasonable prepared script at higher-than-chance frequency.
 
  • #42
Ha, it's amusing that it actually convinced Evo and Ivan that they were talking to real people, I guess the technology is advancing. It's real ( contrary to urbandictionary.com... ).

Here is Rollo Carpenter's (the creator) entry at the Loebner competition: http://loebner.net/Prizef/2007_Contest/loebner-prize-2007.html
 
  • #43
I preferred Cleverbot over omgele
 
  • #44
Cleverbot is really stupid. Phil's chat application uses it, and it is not intelligent at all, despite the large vocabulary. 2-year-olds have a better grasp of communication.
 
  • #45
CINA said:
Ha, it's amusing that it actually convinced Evo and Ivan that they were talking to real people, I guess the technology is advancing. It's real ( contrary to urbandictionary.com... ).

Here is Rollo Carpenter's (the creator) entry at the Loebner competition: http://loebner.net/Prizef/2007_Contest/loebner-prize-2007.html
I'm still convinced that it was not a program, or not all of it. It was random until one point, when it suddenly changed, I won't go into detail about the conversation because it's about someone I know, but it suddenly jumped to an actual discussion with detailed recommendations and concern. They were concerned about me being upset and wanted to know if they could phone me, or otherwise take the conversation to another venue. I declined, so they asked me if I could come back again later that night to try to continue our discussion. That's quite an AI program.
 
  • #46
Evo said:
I'm still convinced that it was not a program, or not all of it. It was random until one point, when it suddenly changed, I won't go into detail about the conversation because it's about someone I know, but it suddenly jumped to an actual discussion with detailed recommendations and concern. They were concerned about me being upset and wanted to know if they could phone me, or otherwise take the conversation to another venue. I declined, so they asked me if I could come back again later that night to try to continue our discussion. That's quite an AI program.

You should have given them an email address and you would have verified it once and for all!
 
  • #47
Evo said:
I'm still convinced that it was not a program, or not all of it. It was random until one point, when it suddenly changed, I won't go into detail about the conversation because it's about someone I know, but it suddenly jumped to an actual discussion with detailed recommendations and concern. They were concerned about me being upset and wanted to know if they could phone me, or otherwise take the conversation to another venue. I declined, so they asked me if I could come back again later that night to try to continue our discussion. That's quite an AI program.

It is possible that they are monitoring the AI chat and have capability of taking over AI. I agree that the bot cannot provide any recommendations or show unique level of concern.
 
  • #48
turbo-1 said:
Cleverbot is really stupid. Phil's chat application uses it, and it is not intelligent at all, despite the large vocabulary. 2-year-olds have a better grasp of communication.

People on the internet can be more stupid than 2 years old, try omgele.
 
  • #49
this reminds me of USENET in the nineties, when about half the annoying forum trolls were accused of being bots.
 
  • #50
CINA said:
Ha, it's amusing that it actually convinced Evo and Ivan that they were talking to real people, I guess the technology is advancing.

Not at all. It was not the complexity, but rather the nature of the responses. It started asking strange and inappropriate questions like, "have I killed anyone". "Would I tell anyone if he [cleverbot] killed someone?" Also, personal information was requested, and everything was completely out of context.

Given the nature of the internet, I try not to take chances. This smells like a scam.
 

Similar threads

First TED talk by a PF staff member
Replies
31
Views
2K
Praise My feedback, one month and half experience in PF so far
Replies
1
Views
3K
One who knows enough to think he is right, but not enought to.... ;)
Replies
13
Views
1K
Finding support to complete a UK charity registration application
Replies
4
Views
137
How Do Our Brains Process Tasks Differently?
Replies
5
Views
3K
I want to help Physics education. What should I do?
Replies
48
Views
831
Where to Pick Up Women In the Sciences?
Replies
11
Views
2K
Historical Novels? (Siege of Malta)
Replies
16
Views
3K
Testing How to not get stressed on the actual exam?
Replies
18
Views
644
What do you think of my site idea?
Replies
7
Views
2K

Hot Threads

Recent Insights

Back
Top