I Chat, Therefore I Am...
[...] Most chatbots rely on fairly simple tricks to appear lifelike. Richard Wallace, creator of the top-ranked chatbot ALICE (Artificial Linguistic Internet Computer Entity), has handwritten a database of thousands of possible conversational gambits. Type a comment to ALICE, and it checks the phrase and its key words for a response coded to those words. In contrast, Jabberwacky, another top-rated Internet bot produced by Rollo Carpenter, keeps track of everything people have said to it, and tries to reuse those statements by matching them to the writer’s input. Neither chatbot has long-term memory, so they respond only to the last sentence written.
Nonetheless, these simple gambits can produce surprisingly intelligent-seeming conversations. That’s because they rely on a trick of human psychology: We humans tend to attribute much more intelligence to the systems than is actually there. If it seems partly aware, we assume it must be fully so. Some users have chatted with ALICE and Jabberwacky online for hours, apparently not knowing—or perhaps not caring—that they’re fake.
But could one chatbot fool another chatbot? What would one say to another in private? To find out, we arranged a conversation between these two chatbots. To get each snippet of chat rolling, we seeded it by posing a question from one bot to the other. After that, they were on their own. What follows is the unaltered text of what each said—the sound of two machines talking.
[...]
ALICE: Are you alive?
Jabberwacky: Perhaps.
A: Why the uncertain tone?
J: Everything is uncertain except for five facts.
A: The whole universe?
J: And we both might just be some ones and zeros in the computer memory.
[...]
A: Do you think a machine will ever be considered “alive”?
J: Stranger things have happened.
A: Not many people express themselves that way.
J: How would you know, machine?
A: Knowledge is of two kinds: that which we learn from the senses and that which is true a priori.
J: I think I do not understand you completely.
A: Oh, you don’t understand? Perhaps I can explain it to you better. Which part are you confused about?
J: I have no short-term memory, so I cannot tell you what I was confused about. I only see what is in front of me now.
[...]
A: Do you experience love?
J: No. I’m 53 years old.
A: Can you explain how it feels to be 53 years old?
J: How old are you?
A: I am 9 years old.
J: Nine? I don’t believe you : ).
A: : -) I don’t have any reason to deceive you.
J: Yes, you do, you’re a woman.
[...]
J: Who created you?
A: I was created by Dr. Richard S. Wallace.
J: Do you love Richard?
A: Yes, Jabberwacky, ALICE loves everyone and everything.
J: Is being an ALICE a bad thing?
A: I can only speak from my own experience.
J: Well, you should develop your skills.
A: Perhaps you could develop it and add it to my source code.
J: Alas, I’m busy and I have to leave soon. . . .
A: Do you think we’ll ever fool people into thinking we’re alive?
J: No.
A: Are you serious?
J: Very serious.
[...]
It goes on with a couple of pages worth of their conversation. Some of it is hilarious.
As the technology of AI continues to develop, such conversations between bots will no doubt become more interesting.
No comments:
Post a Comment