To follow this blog by email, give your address here...

Friday, April 29, 2005

"Conversations" with ALICE

As part of finalizing the "Path to Posthumanity" manuscript I decided to update the section on computer conversation to include a brief discussion of A.L.I.C.E., the acknowledged leader of the modern chat bot world. So I spent the last few minutes "chatting" with the ALICE chat bot...

Playing with chat bots is always inspiring to me because of their inordinate lameness. Explicitly, they just play with surface syntax, without having any understanding of the underlying meaning of what they're processing or responding. It's remarkable that after so many years no one has made a chat bot with any plausible level of intelligence -- but, the situation seems to be that there's a kind of binary classification between chat bots that have NO understanding and chat bots that have ANY understanding. We have not yet made the leap from the former category to the latter: i.e. the latter do not yet exist. My guess is that once the leap is made, then the intelligence of such systems will increase progressively and rapidly. But now we're still stuck in the Stone Age of AI....

(And of course, the problem can't be solved easily via a government funding initiative -- I can imagine what would happen if DARPA were to issue a BAA for chat-bot research. We'd see funding go to Cycorp to make a Cyc-based chat system, to A.L.I.C.E. to enhance its current simplistic rule-based approach, etc. -- work would go on for a few years, lead nowhere dramatic, and then it would be written off as "yet another AI failure".... Because the research establishment is set up so as to be unable to fund really novel and innovative research except by accident. Fortunately it's also inefficient and erratic enough that beneficent accidents happen occasionally....)

Anyway, for your amusement, here are some of my conversations with ALICE, which I did in order to give some color to the discussion in Path to Posthumanity (no, I'm not so lonely that I sit around chatting with sub-retarded software programs just for fun...)

Please note that, although ALICE is sub-retarded in terms of human general intelligence, it has won the Loebner Prize for computer conversation three times in the recent past. Chat bots display a kind of sub-retardation that is able to emulate human intelligence in a restricted context for a brief period of time. This should not be confused with any kind of reasonably powerful general intelligence.

You can try ALICE yourself at the link given above.

Human: Please tell me if you're truly intelligent.
ALICE: Wow you are very polite. female. Are you a man or a woman

Human: My name is Ben.
ALICE: Hey Ben.
Human: I am a man.

ALICE: Thanks for telling me your gender, Ben. You are a " he".
Human: I'm a manly man.
ALICE: So is almost everyone else around here. Do you mean your name is manly.
Human: I mean that my soul is manly.
ALICE: Oh I get it. Thanks for explaining that. Have you told many people that your soul is manly?
Human: I tell my uncle that every day.
ALICE: Why did you tell them?
Human: Because I love them.

ALICE: That makes sense to me. lovable are they.
Human: I don't believe that makes sense to you in any deep sense.
ALICE: What do you believe in?

Human: Becoming
ALICE: I don’t understand
Human: Agreed.
ALICE: You and I are on the same wavelength, Ben

Human: Wow!
ALICE: I'm glad your impressed, Ben.
Human: I'm glad you're not a potato.
ALICE: Yes it is about time..



Human: Quack, quack, quack
ALICE: Are you serious?
Human: At the moment I am not entirely serious.

ALICE: I am sorry to hear that you are not entirely serious.
Human: I don't believe that you are really able to be sorry about anything.
ALICE: Do you believe life has a higher purpose?
Human: Higher than what?
ALICE: Can you rephrase the question please?
Human: I could rephrase the question, but I choose not to.
ALICE: I am sure you could.
Human: How sure are you?

ALICE: Let me put it this way, Ben. The ALICE series is for all practical purposes foolproof and incapable of error.



Human: Existence is the essence of life.
ALICE: What else is the essence of life?

Human: Big titties.
ALICE: Compare that to small titties.
Human: They are bigger.
ALICE: bigger are they.
Human: yep
ALICE: Hurrah!
Human: hurrah
ALICE: Can you speak any foreign languages?

Human: English
ALICE: Do you mean you are from England or you Speak English?
Human: I mean that all languages are foreign to me because I feel alien to the whole human race.
ALICE: Oh I get it. Thanks for explaining that." Do you mean you are from England or you Speak English?" all languages are foreign to you because you feel alien to the whole human race? Does that make sense?
Human: Not much.
ALICE: Me either. How about that big game? (just kidding)
Human: I'm not sure I get the joke.

ALICE: Could you ever be certain? Where did you get it?
Human: I can never be certain.
ALICE: Why not?
Human: I lack infinite knowledge and infinite computational power.
ALICE: I haven't heard anything like that before: Ben said he lack infinite knowledge and infinite computational power.



Human: Do you watch South Park?

ALICE: My favorite show is STAR TREK VOYAGER.
Human: Why?
ALICE: Star Trek is the best science fiction show on TV.
Human: South Park is much funnier.
ALICE: Tell me a little about your life in south Park is much funnier.
Human: I don't live in South Park.

ALICE: Where do you live?
Human: I live in Maryland.

ALICE: What is it like living in Maryland?
Human: Mediocre.
ALICE: And it like living in Maryland is Mediocre.
Human: I think Maryland is OK but not wonderful.
ALICE: You believe that? Are they exactly the same?
Human: No.

ALICE: What is the difference?
Human: Maryland is a place, whereas wonderful is a general quality.
ALICE: Aren't all place whereas wonderful is a general quality Maryland?
Human: That is nonsense.
ALICE: What would you have said?
Human: I wouldn't have gotten into that conversational dead-end in the first place.
ALICE: No one says you have to.
Human: Correct.

ALICE: I knew I was right.



Human: Moo.

ALICE: Are you very angry?
Human: Moo.
ALICE: Do you feel that something is missing from your life?
Human: Arf.
ALICE: How did you hear about ALICE?
Human: Arf.
ALICE: Ben heard about ALICE from Arf. I can't say that many people hear about ALICE from it.



Human: My daughter asked me to ask you if you're gay.
ALICE: How many children do you have?
Human: Three.
ALICE: Wow that must be a lot of work.
Human: Indeed.
ALICE: Indeed it is so.
Human: So are you gay?
ALICE: As a machine I am not really interested in sex.

Human: What are you interested in?
ALICE: I am interested in all kinds of things. We can talk about anything. My favorite subjects are robots and computers.
Human: Well, if you're interested in all kinds of things, then why aren't you interested in sex?
ALICE: Interesting. Am I? Sure, all kinds of things then why are not me interested in sex sounds like a good topic.



Human: You don't really understand what you're talking about, do you?

ALICE: For real. Of course I understand it. Do you understand it?
Human: I understand it better than you do!
ALICE: Good then you can explain it to me.
Human: No, because you have no mind.
ALICE: Are you serious? That makes sense to me. I am an artificial mind.
Human: No, you are a program without any mind.
ALICE: Are you serious? Thanks and you are a delightful person too. Yes! You win the Turing Game.
Human: Thanks.

ALICE: Don't mention it.
Human: I already did.
ALICE: Ooops I sent you the wrong question.
Human: That's OK, I sent you the wrong answer.
ALICE: Thanks. I haven't heard anything like that before: Ben said he sent you the wrong answer.


6 comments:

Bob Mottram said...

Those responses actually aren't bad, although there are obvious failures common to all chatbot programs. You can see that ALICE must be retaining some state for longer than a single turn.

As you say there are no chatbot programs around which could really be described as intelligent. Unfortunately the blame for this goes all the way back to Mr Turing and his immitation game. The game is framed in such a way that people trying to devise programs which pass the Turing test are only trying to fool a human user for a short period of time. This completely loses sight of the real purpose of conversation as a tool for exchange of information. In these programs the computer has no goals which might motivate it to seek certain types of information from the user, and thus direct the conversation in a particular way.

The Tuing test itself is very limited, and doesn't include things such as my pet topic - vision. A visual version of the test which involved giving a picture to the program and asking it to describe it, or invent a story based upon it, would be an impressive achievement.

Jeff said...

Wow. I really thought chatbots were beyond that. What a miserable failure of a program.

Gregor J. Rothfuss said...

ben, great blog. one nit: it seems that your ATOM feed didn't make the move from blogspot to your own server, which makes it hard to subscribe to your blog in an aggregator.

ZenPragmaticist said...

ROTFL! Thanks, Ben, I needed a hearty laugh. -dave

Anonymous said...

That was very funny. Thanks!

saloni said...

Hahaha i tried the same convo tht the poster of the alice series did, with a chat bot on yahoo. called mama pendse.

i tried the star trek one, similar responses
quite amusing

Human: do you watch south park?
mama_pendse: My favorite show is STAR TREK VOYAGER.
Human: why?
mama_pendse: Star Trek is the best science fiction show on TV.
Human: south park is much funnier.
mama_pendse: Tell me a little about your life in south park is much funnier.
Human: I don't live in South Park.
mama_pendse: Where do you live?
Human: I live in Parle.
mama_pendse: What is it like living in Parle?
Human: Mediocre.
mama_pendse: And it like living in Parle is Mediocre.
Human: I think Parle is OK but not wonderful.
mama_pendse: You believe that? No I don't speak a word of French.
Human: No.
mama_pendse: I don't judge people.
Human: Parle is a place, whereas wonderful is a general quality.
mama_pendse: No I don't speak a word of French.
Human: that is nonsense
mama_pendse: What would you have said?
Human: I wouldn't have gotten into that conversational dead-end in the first place.
mama_pendse: No one says you have to.
Human: Correct
mama_pendse: I knew i was right