Of course, from the point of view of the "classical" AI Scientist, the Argument Agent is a fluke. The clever things it might say that convince people that it is "intelligent" do not originate from any "personality" that the machine has somehow developed, like human beings develop theirs. We might soon reach a stage where the AA appears to be the caring, sharing, customer-loving machine any internet vendor would like to employ -- the author, for one, dreams of the day he´ll start to write his first AA for the CYC engine. But the machine can only do this after a clever human being, an artist, a con woman, a trickster, has put the caring, sharing stuff into it. Basically, the AA is just another doll on stage, with artists and engineers pulling the levers from behind a black velvet curtain.[by Dirk Scheuring on the white papers collection at AOK.]
This piece discusses automated Storytelling agents, harkening to HAL in 2001: A Space Oddity and to Doug Lenat's Cyc project. The focus is argument agents, rather than generic storytelling agents, but the problems are similar. How do you move from emotionless, canned responses to something that "feels" more alive and more like a dialog. Eliza is an early form of this and loses its fun factor after about five minutes.