A website that may seem like all fun and games, but it is fake. While you chat to the so called "cleverbot" the only thing that is happening is that you are talking to other users. You only talk to one person for about a few texts, then they change it, which is why you will get such random off-the-wall conversations. If you go to it at first, you will belive it, but if you tell somebody that the website is fake and that this is just two users talking to eachother, then you will most likely recieve a "oh!" That is also why the bot claims to be a human so many times. But it is fun messing with people :D
User:hello Cleverbot: Are you a computer
User: No, you are
Cleverbot: No I am not you are
User: Why do you alway say I am the Robot
Cleverbot: Hello, do you like kool-aid?
(Owned)
A computer system that learns to be clever from real people. But is horribly failed system, who is racist, sexist, stupid and complety waste of time. It is understandable though, it DOES learn from real people, and thats what real people truly are.
user: are you a computer?
cleverbot: no, im a human, for the millionth time
user: kool, what are your hobbies then?
cleverbot: silly, computers cant have hobbbies.
user:u fag
cleverbot: squerrels.
Although many people believe this program is a fake, that simply isn't possible. Cleverbot is real. After playing with it for a while, you can easily see that its answers, while relevant, are too stupid to be human. It can also easily be tricked by a single question, and if you keep asking the same thing, it will start repeating itself. Plus it can recite lyrics. You can't count on some random person to know all the lyrics to a certain song, but I was able to sing Never Gonna Give You Up with it for several posts. One more thing: If you ask a question that's uncommon but easily answerable, Cleverbot will most likely not know how to answer it. All of this proves Cleverbot really is a program.
If Cleverbot was fake, that would make the whole thing about AI and all the tests that were done on it a huge lie. Plus the site assures that you're not talking to a person.
By the way, it makes sense that Cleverbot says it's a human. Cleverbot uses information from replies that it got from previous posts, so when it says "I'm human," that's because of someone else that said they were a human.
Note: These are actual conversations with Cleverbot.
User: What's 25 + 25 + 25?
Cleverbot: I can see out conversation, can't you? (i.e. doesn't know how to answer)
_____
User: Have you heard of this thing called Pokemon?
Cleverbot: Yes. I can be sarcastic when I want to be. ARe you ever sarcastic? (i.e. doesn't know how to answer)
An online "AI" which works by one of two possible methods, and either way, is very clever:
1. Either it is an AI that stores contextualised responses from users and uses them to answer questions of other users.
2. Or it is, as many suggest, simply a service which, after recieving a message from you, sends it to several other users, and then returns one of the replies to you.
If the first is true, it has easily passed the Turing test due to the mere fact that so many people were convinced it was not an AI. If the latter is true, then it is still a very interesting exploration of the concept of the Turing test, online AI conversations and the anonymity and disconnection of online conversation.
It is also just as interesting to get it to talk to itself, although this does not make either of the possibilities seem more reasonable.