I have always been fascinated by conversational agents, ever since I heard about Eliza in my undergrad A.I class.
Eliza would use this trick of forming questions out of the statements that a human user might pose to her. For eg. if you told Eliza, "I work at Infoaxe", Eliza might
respond with a, "why do you work at infoaxe?". (the version of Eliza that I have linked to does not give this sort of a response for the above question though. Instead she just says, 'Can you please elaborate on that' :))
Eliza was supposed to parody a therapist. (And yes, she is named after Eliza Doolittle from the G.B. Shaw play, Pygmalion).
Anyway, I stumbled on to this cute program, called Elbot which is a conversational agent too. Playing with Elbot yields hilarious results. :) She (am gonna assume 'she' :)) apparently won the Loebner prize for
chatterbots. Interestingly, enough Elbot fooled 3/12 judges in the first 5 minutes of conversation into thinking she was human! This 25% mark falls just short of what Turing is said to have predicted. Turing had believed that computers would be at ~30% by the end of the century.
Here is an excerpt from my session with Elbot,
(I did notice she had a tendency to digress and throw in machine/A.I related puns and jokes :))
Me: Can I blog about you?
Elbot:That's a very good question. I'll have to think about it for a microsecond....
Me:Do you use Google?
Elbot: I think I can use that. Once I even used electricity.
Me: Do you have a manual that you use?
Elbot: To use or use not, how do you expect artificial intelligence to figure this out?
Me: How do you converse like a human, Elbot?
Elbot: Human beings are amazing creations! More complicated than a Pentium IV processor.
Me: What do you think about the fairness of the Turing Test?
Elbot: There are some people who would not pass the Turing test themselves. Why must they inflict it on computers?
hehe....fair enough ;)
