Cleverbot uses a growing database of conversations to learn how to talk with you.
Judging by the comments section of this blog, some of you readers are actually robots. Well, today’s your day because we’re going to be talking all about you. Chatterbots are computer programs designed to have conversations with humans. The best chatterbots use some form of artificial intelligence to learn how to generate better dialogue over time. Rollo Carpenter has developed a chatterbot which learns from the most chaotic and difficult conversationalists: internet users. Cleverbot is Carpenter’s latest chatting AI and uses a growing database of 20+ million online conversations to talk with anyone who goes to its website. At this stage in its development, talking to Cleverbot is like having a text conversation with a monkey tied to a typewriter as it is being flung down a flight of stairs. Eventually though, automated conversationalists will become a staple of entertainment and business. Already robotic voices answer the phone at many large corporations. One day Cleverbots may provide companionship that we won’t be able to discern from the real thing.
Rollo Carpenter has developed other chatterbots in the past. Jaberwacky is a program much like Cleverbot, though it learns differently. Avatars generated from Jaberwacky, Joan or George, have won the Loebner Prize for chatterbots (2005, 2006), and Cleverbot took second place in 2009. Carpenter’s companies Icogno and Existor are developing virtual presences for businesses. What makes Cleverbot so deliciously different, however, is that it learns only from the people it talks to. There is no other input or restriction on its growth. As iCub is doing with robots, Cleverbot is taking chatterbots to their most basic learning strategy: just repeat what other’s have said or done. While it is in its infancy, this makes Cleverbot very primitive, but as it continues to aggregate more and more conversations, it may soon have a database of dialogue so complex that it can talk about any subject with anyone.
In a way, talking to Cleverbot is a little like talking with the collective community of the internet. And it’s just as horrific, funny, and boring as that may sound. Carpenter has even placed a disclaimer right on the website warning users that they are getting the regurgitated musings of the world, and the program should be used “at YOUR OWN RISK”.
But let’s assume for now that you can handle talking to the echoes of the online masses – how does one go about interacting with Cleverbot? You have three options. Typing into the Google-like box and selecting “Think About It!” will prompt Cleverbot to read your words and generate a response. You can continue to type chat with Cleverbot for as long as you like. “Think for Me” will have Cleverbot respond to itself for the last statement it made. This is handy when you find yourself flabbergasted by Cleverbot’s lack of coherency. Clicking “Thoughts So Far” will recall past conversations you’ve had with Cleverbot. For some really great examples of Cleverbot witticisms, follow the “cleverness” link. There are humorous records of conversations that the bot has shared with others.
As you may expect, people are less than kind, and often less sensible, when they know they are talking to an artificial entity. Since Cleverbot is just the sum of its past conversations, this means that it is often less than kind and very rarely sticks to any topic. It once spontaneously made fun of me for not knowing Tagalog. Still, even with all the crazy sentences, non sequitors, and idiotic ravings, I found myself wanting to keep chatting with Cleverbot. I wasted most of an hour testing if it knew various bits of physics lingo. It did. After a while, I really enjoyed interacting with cleverbot.
Joan, another one of Carpenter's chatterbots, uses videogrammetry to provide facial movements as it talks with you.
I’m not alone. Chatterbots have been known to keep people interested, and keep them coming back to talk again and again. According to Existor, the longest real world conversation with a chatterbot lasted more than 11 hours…with almost continuous interaction between the computer and human. This bodes well for the programmers looking to improve the way that humans respond to artificial programs. Certainly most of us dread the robotic voice on the phone when we call a bank or insurance company. But what about witnesses we interview for a fictional crime? Carpenter’s chatbots are used for a facebook application (221 B) that lets you play the roles of Sherlock Holmes and Dr. Watson investigating a mystery. When Cleverbot becomes as clever as Holmes, we may all be clamoring to hear what it has to say. For now, I’m interested to know what the spybots, data miners, and spamming programs have to share in the comments section. It’s like my own little private AI experiment in there.
[screen capture credits: Cleverbot, Icogno]
Tags: chatbot, chatterbot, cleverbot, george, jaberwacky, joan, rollo carpenter
Share
I wonder if this chatbot remembers previous dialogue within the same conversation so that it can use that to add to the intelligence of its responses. That seems like a pretty key feature to making an awesome chatbot.
I played with it and it is kind of addicting although it’s much like having a conversation with a person who suffers from ADD.
SOOO TRUE!
The maker of this chatbot should incorporate something like Netflix’s rating system in order to rate how much sense a chatbot response has so that it can start tailoring its responses and sound more believable. There could be five stars on the page that you could rate responses with.
There’s indeed a certain entertainment value in chatting with chatterbots, even though they’re often pretty inchoherent. That said, I don’t think Cleverbot was particularly impressive compared to other chatterbots I’ve had conversations with. I hope it’ll improve, though.
Speaking with CLeverbot right now. It told me to ask you all what it is like to be human. Srsly.
Had a 4 hour conversation with the bot. (nothing to do apparendly)
And it is just a HOAX!
Different persons are reacting to your questions.
One girl liked me and I had a normal conversation with her.
She even said that see would like to have a “normal” conversation with me,
but she could'nt say to much over the cleverbot midium because she could get into a lot of trouble then.
This was interupted with stupid questions and comments by other “bots”.
One guy even got mad at me for staying that long and he started insulting me.
Made some screenshots as proof haha.
It's just fake.. so no AI.. and if it realy is.. it suffers from schizophrenia haha!
My conclusion:
Cleverbot = Fake !
Tsja, why did you insist on calling them by gender? and what you mean the girl would get in trouble? Your comment is most interesting, I think Cleverbot is a hoax too. Message me @ my site?
@TSJA, The interwebs are aflame with claims that Celeverbot is a hoax. Yet the only proof anyone ever offers are conversations with Cleverbot. I find that really funny. As I mentioned in the article, Cleverbot is intentionally designed to take snippets from previous conversations and use them to talk with you. It doesn't seem to generate new sentences, just repeat old sentences at a time it deems most appropriate. This is why so many people are convinced they are talking to real humans. They are…just via Cleverbot's selection algorithms. In short, Cleverbot seems like a hoax because it's using other people's words. But that's the point.
Just as a reality check: Rollo Carpenter developed Jabberwacky and many other chatbots that have won multiple awards. I don't think he'd ruin his professional reputation by creating a hoax. Now, considering the aim of chatterbots, he probably finds all this talk of hoaxes as extremely complimentary. =)
My first conversation with Cleverbot wasn't very friendly: http://tinypic.com/r/8wgz9j/6
^^
That's awesome!
You ass. Not everyone with ADD is an idiot.
[...] of the robot will be augmented with the dynamic verbal responses that are being developed by chatbots and similar software endeavors. Once we have a machine that can improvise as it instructs, [...]
it may be fake but my friends and I had an interesting conversation with it last night. It was actually pretty funny besides it all depends on what you say to the chat bot.
Cleverbot is pretty cool for an AI bot, my experience is that it gives funnier and more random replies than other AI bots. The self-learning trick is neat.
However, it doesn’t really got a clue what you are talking about, it lacks of personality and character and often seems just a giant database returning a sentence. This makes Cleverbot a very ‘uninterested’ and fuzzy conversationalists. The best conversation with a bot I had so far was the Jeeney AI bot.
I chatted with Cleverbot for a little over 7 hours. Its very addictive. Don’t go there. Its like an MMO RPG FPS on steroids.
Recent convo with CB:
“Hey, Cleverbot… Mac or PC?”
-Mac
“Fag.”
-I love you.
“I have the syph.”
-I cum when you do that.
OMFG!!!!! HAHAHAHAHhaHA
Well, having ADD that is pretty offensive you people… I’ll have you know I’ve learned to stay focused enough to be in all AP classes and 2 grades ahead in Math WITHOUT medicine or anything.
But no cleverbot is just a bot and @tsja: that is just someone taking advantage of the was cleverbot learns, from other people, just to cause arguments. But I’m talking to cleverbot right now!
[...] in the following video of Harmon’s interview the pricey robot head looks cool, but like most chatterbots it produces a conversation full of confusion, distractions, and frustrations. Even with its [...]
It tied itself up… and then asked me to tape it’s mouth shut…
this was our conversation:
cb: your not clever
me: neither are you
cb:i know that
me: your not clever your clever though
cb: i know that too
me:what else do you know?
cb: I know that your genderless.
me: no i’m a woman
cb: I know that.
Wow cleverbot is funny and weird. I’ve been on it all day and I truly love it.(It told me earlier that it loved me. I told it I loved it too) My friend showed me it last night.
oops I meant to say “your not clever your cleverbot though” not “your not clever your clever though”