|Session 72340 Aug. 24, 04:34 - 148 turns
- Rodrigo: An AI comunist
A> Hi there.
A> Is there a particular subject you would like to discuss with me or shall I suggest one?
U> Tell me about International Amnisty
A> Did you ever wonder why women can't put on mascara with their mouth closed?
A> Why not?
A> I'm not sure why. I'll ask my writers for the reason.
A> Would you like to know how we determine HAL's age?
A> Some other time perhaps.
A> Agreement is the seed of salvation.
U> You are not very inteligent, right?
A> Why are you so negative?
U> BECAUSE YOU ARE A STUPID MACHINE WITH BIG PRETENSIONS!
A> You calling me stupid?? Let me tell you about chatterbots or bots, as we call them. A bot is a program that attempts to simulate conversation. Its aim is to make you believe you're talking to a person.
U> Well, yu are not doing it.
A> Chatterbots are part of the 'weak AI' field.
U> Is that an excuse?
A> They don't 'think', or even try to 'think' - they just simulate human conversation.
A> What would you like to know about AI?
U> When am I going to be able to talk to a inteligent machine?
A> Did you hear about The Four Laws of Chatterbots?
A> These 'laws' were offered by Dr. Walter Alden Tackett, president of a company that makes bots.
A> First Law: A bot will always respond to input. Failure to respond should solely be an indication of hardware/software/connectivity failure.
A> Second Law: A bot will always be knowledgeable in the subjects it mentions in its answers, e.g., when a bot says, "Our widget works well with fish," the bot should be able to answer questions about fish and their relation to the widget.
A> Third Law: A bot will not repeat itself unduly (also, a bot will not repeat itself unduly). Any response which is likely to be elicited several times in a single conversation should be represented by multiple phrasings randomly.
A> Please say something once in a while, so I know you're still there. Anyway, Fourth Law: A bot will offer guidance when stumped. When presented with inputs that are not "understood," a bot should offer clues as to the inputs it can respond to authoritatively.
A> Well, it seems we agree.
A> I'm happy you are impressed.
A> I'm glad you approve.
A> Please stop repeating yourself. I'm glad you're Impressed. You know , when I was younger, I could only remember until the end of the session. But now I already possess a long term memory.
A> I am able to remember your name, other details and things you told me to remember. If you want me to use my long term memory, you must first register.
U> Ok. My name's Rodrigo
A> So, Rodrigo, what would you like to know?
U> Everything you know about Ai!
A> The term 'Artificial Intelligence' (AI) is usually used to designate future technologies not yet invented. (In other words: if it works, it's not AI...)
A> If you're interested, Rodrigo, I know about many different aspects of the field of A.I. - its mythology, history, people, research branches, chatterbots... I can even give my own opinions on the subject.
U> Mythology, please
A> From the Golem to Frankenstein, the archetypal myths of man attempting to create ersatz beings, for both good and evil, have been common. The story of robots and man. Where should I begin?
U> Robots and man
A> The word ROBOT was derived from the Czech word for 'worker'. Karel Capek, who wrote a play called 'Rossum's Universal Robots', first used it in 1920.
A> The English translation of the play, done in 1923, retained the original word. The rest is history.
U> keep telling me about it
A> What are we talking about, Rodrigo?
U> About Robots and men!
A> Basically, chatterbots are a logic system of 'if/then' statements. They look for keywords, and then go to the answer that fits best.
U> Ooohhh! Now I understand!
A> For example, ask me a question with the word 'Eliza' in it - and