unning the gamut from existential thoughts to completely nonsensical talk, robots at the annual Loebner Prize competition strove to capture the nuances of human conversation, showing that despite much progress, they still have a ways to go to sound convincingly human.
Margaret Wertheim of the
visited this year's Loebner competition, where judges sit at computer terminals holding typed conversations, some with the chatterbot robots, some with actual humans. The judges then must rate their conversation partner on a scale of what percentage human he/she/it sounds. The following is a sample of the robot Alice's conversing skills, the winner of last year's competition:
JUDGE: Are you a tree frog?
PROGRAM: Am I a tree frog? Only when it matters.
JUDGE: When does it matter?
PROGRAM: Only when I have the proper programming.
JUDGE: And do you have the proper programming?
PROGRAM: Is there only one proper programming?
JUDGE: Can you do arithmetic?
PROGRAM: Doing arithmetic is not among my strongest traits.
JUDGE: Are you willing to try?
PROGRAM: I don't know whether or not I am willing to try. I am a giant electronic brain.