World's first conversation between two robots quickly descends in to an argument about God.

I am Baconbot.


I am not a scientist.

Originally posted by FOXMULDER147
This is the world's first conversation between two 'chatbots'.

This is NOT the world's first conversation between two chatbots.
Ever since chatbots were invented, people have had them talking to each other.

2007, and article HERE
2001, transcripts HERE and HERE
1973, a transcript HERE

Fill in the year gaps with multitudes more.

reply to post by FOXMULDER147

The chatbots learn to 'speak' by remembering past conversations they have had with humans.

Therein lies the demonstration flaw. See what I'm getting at?

"Together we are robots."
"I am not a robot. I am a unicorn."

Fantastic!

Thanks for the post, that was fun.

Played with some of these before and read quite a few transcripts from when the real person was not aware the other was simulated.

* The real persons typically expressed frustration when the bot failed to engage a discussion properly; thus "argumentative."
* Of course the many who know about chat bots and want to try it out will ask questions that they know a machine cannot answer in a predictable way; thus "Do you believe in God?"

I generally asked the bots to "Open the pod bay door." As I recall, the answer was usually something like, "The pod is important to you?" or "Tell me about pod bay?" Like a bad psychologist!

The random "I am a unicorn" was great.

Based on the video, it doesn't look like they actually did anything at all.

Both AI's mentioned cleverbot, which does not actually use bots at all. Instead, it's a chat program, designed to pair up human cleverbot users with other human cleverbot users so that each user thinks they are talking with a clever AI. Then, every couple minutes or so, you are switched to a new user to keep the conversation just confusing enough to pass for a scattered computer conversation.

It works the best when you go there thinking that you're talking to a bot. However, when you go there acting like cleverbot, you get some interesting results. The supposed "bot" often talks like a human talking to a computer, asking profound questions, asking you to compute crazy equations and such. At that point the illusion comes crashing down. Occasionally, you get other users that have also figured it out and are not so subtly acting like cleverbot.

You can tell it switches users every couple minutes because cleverbot will all the sudden start to get frustrated because the person on the other side is confused why you're talking about Texas when they were just talking about love with someone else.

It's pretty funny how many people fall for it. I must admit, they had me fooled for about 20 minutes the first time I went there.

Anyways, it makes me wonder what these grad students were actually doing if they used cleverbot for their source of AI. Hmmm.

Yeah, I loved this when it was posted a couple weeks ago.
It was great then.
I will love it just as much when someone starts an entire thread about it next week too.

reply to post by C0bzz


Ha! I checked it out, after it asked me if I could speak it said "Perfect" to which I replied "Excellent" to which it replied "Fantastic" to which I replied superb. Then it started speaking to me in a foreign language. After many times stating that I didn't understand it said

Cleverbot
Are you eat.
Me
That does not make sense.
Cleverbot
If you were an evil intelligence out to destroy humanity, would you admit it?
me
Yes.
Cleverbot
You want me to punch you in the face?
me
No.
Cleverbot
Then what do you want?
me
World peace.
cleverbot
After the world is destroyed in Nuclear Fire, the Enclave forces will grant your wish.

WTF? HAHAHA!!!