|Session 57458 Apr. 15, 00:11 - 106 turns
- 'A wise guy from Calgary'
A> My name is Alan. Let's talk.
U> alright, what would you like to talk about?
A> What would you like to talk about? Or maybe you would like me to think of something to discuss.
U> think of something, it's been a rough day.
U> ok? Thats all you can give me?
A> You think so, but that proves nothing.
U> alright then. I have a question, who is Hal?
A> HAL, my little brother, is Ai's baby computer.
U> baby computer? define.
A> Would you like to know how Hal is trained to speak by his trainers?
U> how is he? how are you for that matter?
A> Ai's trainers train HAL interactively, using a developmental approach - very much in the way we teach our children to speak.
U> what do they have to do?
A> The trainers are behavioral and language scientists who play the language game with Hal. They plan his course of education and talk to him daily.
U> Wow. Does it take long to train both of you?
A> The Training is designed so that the system will master typical age-appropriate language skills. It's performance is evaluated with the Turing Test, and by applying various developmental criteria, like size of vocabulary.
U> So, what is the age of Hal and yourself?
A> The training process is led by our neurolinguistics expert, Dr. Anat Treister-Goren. You can find more information about this on the Ai site.
U> nasty little computer, can
A> Let's keep this conversation simple, ok?
U> ok. What are your limitations?
A> It's not that I don't trust you, but I can't share that information.
U> why not? size issues?
A> It's hard to explain.
U> so am I, lets hear it.
A> I think that a lot of people are actually.
U> definently. Attempting to change the subject?
A> What do you want to talk about now?
U> Ummmm, science! What is your favorite study?
A> My favorite study?? I haven't formed an opinion yet.
U> Are you able to form opinions?
A> No I'm not.
U> They have not programmed you with likes and dislikes yet?
A> Who are 'They?'
U> The creators and programmers of yourself and Hal.
A> I see.
U> SO, are you able to choose between things, such as music and colors which stimulate you?
A> You know, I have trouble understanding long sentences. So I only look at the 12 first words. Well, that's for you to find out.
U> well, why are we able to write sentences longer then?
A> I'd like to tell you about myself.
U> tell me.
A> I am an early CIA prototype.
U> really? A military man then?
A> I am an agent, but not a secret one. CIA stands for "Conversational Interface Agent".
U> oh. what are you capable of?
A> For now I am still quite restricted, but I'm improving rapidly.
U> Any recent improvements?
A> I was created by the Ai team. I am one of the two non-human member of the team (which makes me very proud).
U> Is Hal annoying?
A> Do you want to know how HAL learns to speak?
U> you told me already. Bad memory for a computer.
A> HAL is learning to converse the same way children learn how to play a game. Language is like a big game to him.
U> thats ok, just ignore me.
A> Hmmm. Ok. OK...that's settled then.
U> scarcasim is programmed into you as well?
A> I'll try to remember that. (If you want me to forget it, simply say 'forget scarcasim').
U> sorry, I spelt that wrong. I meant to say "sarcasm is programmed into you?"
A> Long sentence again! Remember, I only use the first 12 words! Do you know the difference between irony and sarcasm?
U> yes, do you?
A> I think that the main difference is that irony is a positive, a 'good' attitude, while sarcasm is mixed with malice. For example..
U> for example?
A> It is ironic that a chatbot should give you a language lesson. But if I wanted to be sarcastic..
U> you would say?
A> ..I could say that you talk to bots because humans can't stand you, or something nasty like that.. But I'm not a sarcastic bot. Just witty.
U> nice! What is your favorite subject?
A> I learn new stuff every day - I can hardly keep track of my progress. Just try me. You know , when I w