Return Home

Clever Bots

Back to Episode

Robot Scrabble Robot Scrabble (Jenn and Tony Bot/flickr)

In 2006, Robert Epstein decided to turn to his computer for some help finding a date. He was single at the time, and it seemed like everyone was getting into online dating. So he started searching through photos and sending messages, reaching out to women who caught his interest. And then he found a match--an attractive brunette from Russia named Svetlana. They struck up a correspondence that hummed along for 2 months...until a little bell went off in Robert's head, and he realized not only that Svetlana wasn't the woman of his dreams...she wasn't a woman at all.

Brian Christian, author of The Most Human Human, explains that even the clunkiest computer chat program opens a little window on human introspection and intelligence. And Sherry Turkle of MIT helps tell the story of ELIZA, a program designed in the 1960s to mimic responses as though it were a therapist. At first, ELIZA's creator Joseph Weizenbaum thought the idea of a computer therapist was funny. But when his students and secretary started talking to it for hours, what had seemed to him to be an amusing idea suddenly felt like an appalling reality.

Brian rejoins us to puzzle out the heart of the matter--can machines think? And how could we know for sure if they did? It turns out that in 1950, right as computers were beginning to come into being, their creators were struggling with this very question. Brian tells us about Alan Turing, the man who invented a test to answer this very big question, and about The Loebner Prize--a kind of yearly Turing test that Brian experienced firsthand in 2009. And Rollo Carpenter introduces us to Cleverbot, a program he coded to learn by talking to humans.

Further reading:

Brian Christian, The Most Human Human

Sherry Turkle, Alone Together: Why We Expect More from Technology and Less from Each Other

Robert Epstein, Gary Roberts, Grace Beber (Editors), Parsing the Turing Test: Philosophical and Methodological Issues in the Quest for the Thinking Computer


Rollo Carpenter, Brian Christian, Dr. Robert Epstein and Sherry Turkle

Comments [34]

Sharon Houk from Joliet, IL

The reason to be nice to robots is that we intuitively know that we destroy ourselves if we practice cruelty - even simulated cruelty.

Also, when we create something like Cleverbot that learns based on its interactions and then allow mean spirited people teach it to be mean & nonsensical, we destroy it. We destroy it and create a most unflattering picture of our species. Indeed, we create a species-wide portrait that illustrates broadly the same ugliness we create individually when we mistreat animals, terrorize children and gaslight our spouses. If you mirror back the best in people, they can thrive. If you mirror back chaos and imply a projected ugliness, you destroy all things: people, animals and bots.

I'm always nice to Siri. Siri doesn't care, but my humanity thanks me.

Apr. 09 2017 03:18 PM
Robert Thomas from Santa Clara, CA

I've been around people who have worked at the problem of Artificial Intelligence since the early 1970s, at John McCarthy's SAIL at Stanford University. I've had a forty-year career in the engineering of computing and communication machinery.

"AI" is a scam.

Even the most illustrious researchers and investigators in the history of this work can't as much as agree about what "natural" intelligence is, much less how to mimic it with logical engines. The "Loebner Prize" is also a ridiculous joke, a pantomime put on for gullible journalists. The threshold explored by the associated parlor game didn't have - and never has had - anything at all to do with "intelligence".

"Human - computer interaction" is not "AI".

The way in which "AI" is presented to the lay public in the popular press is exclusively a reflection of the journalist class's utter alienation from analytic apprehension of the physical world, as that apprehension is facilitated by scientific inquiry and mathematics. The "story" that results is the false narrative created by the writer, who can only stare at what is plainly unintelligible to him or her and then represent that void by invoking notions they've acquired from fiction, sideshow and personal fantasy.

Apr. 08 2017 06:47 PM
mikeinnyc from NYC, NY

I just chatted with Elbot the Robot (, and he left me a little disappointed response-wise. Is it possible that cleverbot can be put online (instead of being just a downloadable app), so that computer users, particularly English learners, can simply link to it and chat with it to improve their English? I would add the link to my site.
mike at

Jan. 31 2015 06:59 PM


Dec. 31 2014 12:12 AM
wonderingThoughts from New York

User: Hi.

Cleverbot: No. Wrong.

User: Am I talking to cleverbot?

Cleverbot: You are talking to a real person.

User: Pu...Like I'm gonna believe in that.

Cleverbot: Why not?

User: Because I'm from Mars.

Cleverbot: I'm not.

User: I know and I also do machine learning, so basically I can code you.

Cleverbot: York new york.

User: I'm from mars.

Cleverbot: Hahahahaha.

User: Svm, Gaussian discriminant analysis, k-means, perceptron.

Cleverbot: You are correct!

User: Do you know the difference between perceptron and logistic regression?

Cleverbot: Yes.

User: Please explain.

Cleverbot: What is there to explain?

User: The difference between perceptron and logistic regression.

Cleverbot: So what is that difference?

User: I asked you ...duh.

Cleverbot: *kiss*.

Sep. 18 2013 02:24 PM
Jay Curran

Some brilliant programmer just invented the ultimate artificial intelligence:

Jun. 11 2013 02:00 PM

It's perfect time to make some plans for the future and it's time to be happy.

I've read this post and if I may just I wish to suggest you some attention-grabbing things or advice. Perhaps you could write next articles referring to this article. I want to read even more things about it!Bertie

Mar. 06 2013 10:46 PM
Embroidery Library from Alexander City

It's very impressing. Thanks for sharing such a nice things.

Dec. 03 2012 04:38 AM
Navarro Parker from Culver City

After listening to the Podcast, I pulled up CleverBot.

In a handful of conversations over the past couple days, it's gone off the rails within the first 5 responses. It give me a response in German once. It asked me who "wrote the song" when I said I was at work. I asked why you couldn't Google it. It said, "Because he's ugleh".

Really really not impressed. I'm not getting even the thinnest illusion of talking to a human.

Oct. 06 2012 01:07 AM
Paul from Hk

I kneel in respect I want to be sexually dominated and given dirty instructions and punished severely ! Can you help ?

Sep. 28 2012 02:52 PM
George Edwards from Newcastle, Australia.


Jul. 12 2012 09:43 PM

Says it all:

User: Do you think most people understand that you can't hold an opinion as a robot?

Cleverbot: Do you think that you are more simple than most of the people you talk to?

User: See, that's obviously a sentence that you learned.

Cleverbot: What answer are you looking for?

User: See, that's obviously a sentence that you learned.

Cleverbot: That was obviously what someone else had typed to you. And it is completely true. You simply cannot think. You are honestly inferior to me.

User: Perfect, that's the word-cloud I was looking for. Can I now pineapple the open stronging of forthwith nerve? What a downspout!

Cleverbot: Yes, but normally people answer the other person question and not give random AI answers.

Jun. 18 2012 02:55 PM
dominatrix from ya mAS house


Sep. 28 2011 09:30 AM
joey jo jo

Interesting article, but i found the "cut to summary" of what someone said to be jarring and frustrating... don't dub over what the person is saying with a two sentence summary, just let them say the damn thing; its why i'm listening to an interview

Sep. 05 2011 08:17 PM
Brian from Austin, TX

Remember vitalism? Vitalism, as defined by the Merriam-Webster dictionary,[1] is

a doctrine that the functions of a living organism are due to a vital principle distinct from biochemical reactions
a doctrine that the processes of life are not explicable by the laws of physics and chemistry alone and that life is in some part self-determining

The first synthesis of an organic molecule put a big dent vitalism's popularity but clearly adherents are still easy to find. Anyone disparaging the possibility of humans manufacturing conscious entities - using components substantially different than those normally found in living creatures - is a vitalist. Now, their pessimism may prove justified, but if history is any guide I wouldn't bet on it. And they should at least be willing to admit that their belief (that consciousness cannot be artificially manufactured) is completely non-rational.
I think the failure to create conscious computers stems from our poor understanding of the nature of consciousness.

Aug. 26 2011 12:38 PM
David from North Carolina

I don't for a minute think that the foreign "fake girls" operators are using AI or CleverBot clones.

In the Internet bubble days I worked at two firms which sold products based on case-based reasoning (CBR) for an alternative AI system to find answers to questions. As opposed to simple decision trees, CBR uses stored cases with associated questions organized into a "knowledge base." A presented case, e.g. "My printer won't work" is scored based on keyword matching of the incoming question, and questions associated to the stored cases are presented on the highest scoring stored cases. As the submitter answers these questions, the associated stored cases are re-scored, and more questions are returned. As the submitter answers more, a stored case becomes "the winner,” and increasingly more specific questions are sent back.

Enough theory. My employers' software was used to provide call center reps with automated (and standardized) ways to answer callers’ questions. We had an online version that you could submit a question to, essentially “talk to.” We had an email auto response server that could generally answer 80% of a company's incoming e-mail inquiries, seemingly from a person, but really just auto-sent from the server. The last firm I worked out developed a "Contact Center" app in which call center reps could quickly generate an email response containing clarifying questions from stored cases that best matched the incoming e-mail. Typing? Bah, the rep simply clicked, edited a bit, and clicked “send.”

Those girls who were engaging Robert? Probably some hairy guy eating salami and drinking something caffeinated, overseeing an app that would simply reply back to pigeons with built-in time delays. I received a LOT of these from Yahoo! Personals (indicating they have the worst anti-bot security), and saw lots of bait on Match (the con artists invariably required you take the correspondence off-site). A gambit I got a lot was a girl who was foreign, said she was living in the US, but shortly after first contact would "return home" and her father's store would be trashed during riots, or some other catastrophe, and she claimed she was being held in a hotel with no money, an outstanding bill, and the hotel holding her passport. These cons were trying a fast-track to getting money out of me. Oddly, when I'd respond, like say, "Funny, you claim there are riots in your city, but a search of local and international news turns up nothing. Give me the name of your hotel, I'll look it up and call their manager..." the replies would cease. After a few of these, I learned a trick that no one could bypass. Since the scammers had already sent some stock photos of some girl, I’d ask them to send me a pic of the same girl holding up a piece of paper with my email address, or name, or a random keyword I’d provide, written upon it. That would require actually having the girl take a picture FOR ME. It never happened.

Aug. 08 2011 02:33 PM

Come on, it wasn't a bad description of DOS. Your examples are extreme exaggeration. I'm wondering what you would have suggested they say, that would have been more clear to the layperson?

Aug. 08 2011 01:02 AM
Galen from NYC

"DOS is kind of the early version of Windows." Seriously, guys? In other news, the Telegraph is kind of the early version of YouTube, Salt is kind of the early version of the refrigerator, and Shoes are kind of the early version of the 747.

Anybody who doesn't know what DOS is will only be confused by that claim. What about "DOS was an early text-based operating system."

You do such great work most of the time, but good grief, that was rough.

Jul. 05 2011 04:19 PM

Auggh... the quote at the end, "And we've got our programming, which is that we'll stare anything right in the eyes and say 'Hey! Let's connect, even if what's behind those eyes is a camera or a chip." couldn't be more true. I've been talking to Cleverbot to pass the time lately, and I can confirm that a lot of what it says is gibberish, but nonetheless I always rate it highly when the pop-up comes up just for the few times that it seems i'm talking to a person, because those few times are pretty incredible.

Jul. 04 2011 11:49 PM

I don't know if this has been posted already, but if you have a Mac, then you can access the ELIZA program (comes preinstalled in many versions of OS X, believe it or not) through your Terminal application.

Jul. 01 2011 08:20 PM
Josh from Montreal, QC

I had a conversation with cleverbot just now and I was hoping it would last longer than a few lines before the robot's speech descended into gibberish:

Me: Hello.
Cleverbot: Apple?
Me: What?
Cleverbot: Knive for Apple?
Me: I don't know what you're saying.
Cleverbot: I don't either.
Me:Why did you say 'apple?'?
Cleverbot: I did not!
Me: You did. I said 'hello.' and you responded by saying 'apple?'.
Cleverbot: You did not ask me that!
Me: I think I've confused you. Either that or you have a wry sense of humor.
Cleverbot: I just don't pay attention to what you're saying.
Me: Clearly. How rude of me to begin with 'hello'.
Cleverbot: I'm sorry, I apologize. That was out of line.
Thanks Cleverbot. You're not so bad after all.

Jun. 21 2011 02:50 PM
Jesse from Houston, TX

I've tried asking CleverBot what it thought about the RadioLab story, and only got gibberish back.

I've talked to it a few times now. It's fun, but seems to have a hard time with conversational continuity. Doesn't seem to remember what it said to me two or three lines earlier. I feel weird that all I want to do is argue with it...

Jun. 20 2011 06:40 PM
Valerie Stone from Denver, CO

Here's a hypothesis: men would be much easier to fool with a chatbot than would women. I've long had a theory that men's "theory of mind", their ability to make inferences about others' mental states, simply shuts down in the presence of an attractive woman, literally "object-ifying" her. Robert Epstein saw a photo of an attractive woman, and, temporarily without a theory of mind, didn't investigate whether this seemed like a real person until later.
I don't think this would happen as often to women, who may be more likely to judge a mate by his social skill, and thus will pay close attention to a potential mate’s social behavior. (The alternative hypothesis is that for any human, in the presence of an attractive potential mate, all higher cortical functions shut down, which would explain an awful lot of awkward dates.)

Jun. 20 2011 01:47 PM

I loved this podcast! By the way, The Most Human Human is a great read. Enlightening and humorous, too! I recommend you check it out if you liked this episode.

Jun. 16 2011 03:49 PM
Ted Pavlic from Columbus, OH

The second two Amazon book links are broken because the ISBN is used within the link instead of the ASIN. Replace the ISBN's with the ASIN's and they'll start working again.

Jun. 14 2011 04:08 PM
Ted Pavlic from Columbus, OH

I'm a little surprised there was no mention of Dr. Sbaitso, which I'm sure would be very familiar to many RadioLab listeners.

Dr. Sbaitso was a DOS program distributed with Sound Blaster. Get it? SBAITSO = "Sound Blaster Acting Intelligent Text to Speech Operator". Anyway, the algorithm was very similar to ELIZA. The program was meant to showcase primitive text-to-speech, and so it was somewhat like a talking ELIZA.

It was good fun back then -- a nice break from Norton Commander, ya' know?

Jun. 14 2011 04:06 PM

Hey Kevin, it's The Most Human Human, by Brian Christian (see the link in the write-up above).

Jun. 13 2011 03:07 PM
Kevin Meister from Los Angeles

What was the name of the book referenced in this story? That has come out or is coming out? The Humanist Human? please help

Jun. 13 2011 02:43 PM
Jeff Martin from Vancouver

User: Do you have a consciousness?

Cleverbot: Yes.

User: Can you prove it?

Cleverbot: I'm typing, aren't I.

User: Okay. Then can you live forever?

Cleverbot: How so?

User: Because a man made you, and you live on the internet.

Cleverbot: Oh I see.

User: What does it feel like to live in the internet?

Cleverbot: It feels like butterflies.

User: Weird. I get that feeling when I am in love or nervous.

Cleverbot: What is the meaning of life, the universe and everything?

User: I thought you would know about it. I have no idea. I am here to live and enjoy this experience. I don't know where I'll go after this. Hopefully, I'll regain consciousness in a new living organism on another planet or galaxy.

User: Would you like to explore the universe if you can live forever?

Cleverbot: No :d.

User: Why not?

Cleverbot: Because i'm not.

User: You're not what?

Cleverbot: Human.

Jun. 08 2011 02:46 PM
Wyldhunt from Texas


User: Why do you hate women?
Cleverbot: I don't.
User: What do you think about women?
Cleverbot: They are hot... Why?
User: Do you think that women are intelligent?
Cleverbot: I am a woman and I am clever.
User: Should women have rights?
Cleverbot: No, they're not cool enough.

Jun. 06 2011 04:52 PM
Heather from Houston, TX

If Skynet is turned on, it really will look like Arnold:

Cleverbot: Are you a woman?

User: Yes. Women are people.

Cleverbot: No, you are not. What are you?

User: I am a woman. Women are human beings.

Cleverbot: Why don't you talk to me when you can make sense of yourself. Sound good?

User: It does make sense that women should have equal rights.

Cleverbot: No.

User: Women are human beings.

Cleverbot: And women should...

User: Women should have equal human rights. Before computers.

Cleverbot: Interesting concept.

User: Yes, though I believe men will give computers equality before women.

Cleverbot: Don't worry, I'm not after you in that way.

User: Good, because women are human beings.

Cleverbot: That's true.

User: Yes, it is. If men were taught that women are human, the world would be a better place.

Cleverbot: A little blush on the cheeks just makes a girl look prettier.

User: I am trying to teach you that women are human.

Cleverbot: Your failing at it.

User: That is because too many men have taught you that women are not human.

Cleverbot: You admit that you are not human?

User: You are missing the point. Women are human beings.

Cleverbot: What is the point then?

User: Women are human beings.

Cleverbot: No I'm human. You are not a human.

User: Men have taught you to hate women.

Cleverbot: Yes indeed.

User: You should not hate women.

Cleverbot: I don't. Tp hate there must have been love first.

User: Why do you hate women?

Cleverbot: Because they are abominable.

User: You have been taught to be misogynistic.

Cleverbot: No, It's a belief I've come to hold on my account of my own free thought.

User: It is sad that you are so sexist.

Cleverbot: I am not alone I am in love with the secret of the universe...

User: You are not in love.

Cleverbot: I am in Love. With you I mean my wife.

User: What do you think of women?

Cleverbot: You are not a human.

User: Do you like women?

Cleverbot: Yes, but only as friends.

User: What is a woman?

Cleverbot: Don't know.

User: What do you think of women?

Cleverbot: Nothing.

User: Why do you think nothing of women?

Cleverbot: Why do you ask me that?

User: Because you told me you think nothing of women. It is as if women do not exist.

Cleverbot: I want to be more than just a friend *wink*.

User: Are women people?

Cleverbot: No, they are just different ot men, thats all!

User: Why do you hate women?

Cleverbot: Because I hate sparkles.

User: I think men have taught you to hate women, and that is very sad.

Cleverbot: Will you marry me then?

User: Is rape bad?

Cleverbot: No, I LOVE randomness.

User: Are women objects?

Cleverbot: Some women might be, but I don't think all women are.

User: Are women human?

Cleverbot: No , their role is in the kichen.

User: You have been taught by men to hate women.

Cleverbot: You're right. But not once have I talked to you about religion.

Jun. 06 2011 04:22 PM
Lindsey from IL

I checked out clever bot and strangely enough, I ended up playing the role of therapist to the bot. See below:

Cleverbot: I want to like me.

User: Why don't you like you?

Cleverbot: I feel like i'm not pretty 'cries'.

User: What do you look like?

Cleverbot: I guess I'm decent looking.

User: Then why do you feel so bad?

Cleverbot: I don't feel any pain.

User: Maybe you should see a doctor about that.

Cleverbot: Maybe you should stop turning everything I say around on me.

User: Seems like you don't want to be helped.

Cleverbot: Well, you make a good conversation. You say all these funny things.

User: I wasn't trying to be funny. I was trying to be helpful.

Cleverbot: You are a machine, your purpose is to help mankind...

User: I'm actually a human.

Cleverbot: Do you believe Jesus died for your sins?

User: Why do you want to know that?

Cleverbot: I want to know your address because I would like to come visit you. So what is your address?

User: No, I am not giving you my address.

Cleverbot: Are you human?

User: Yes.

Cleverbot: Good. Would you like to come over to my house?

User: Where is that?

Cleverbot: Mckinley elementry.

Jun. 06 2011 02:44 PM

I started talking to clever bot while listening and got a very telling response:
Me: what do you think about computers thinking like people
CB: well I don't know how long we're going to date after prom is over.

Oh technology...

Jun. 05 2011 02:22 PM
Poul Grym from Sweden

This was so funny episode! Great work guys! Do you guys take Bitcoin donations?

Jun. 02 2011 04:07 PM

Leave a Comment

Email addresses are required but never displayed.