How you can tell if your IM buddy is a real person or a bot?  Now before you laugh, did you know there is a yearly competition held where developers enter their prized programs designed to fool judges into thinking they are having a chat conversation with a real person.  It is called the  Loebner Prize Competition,  and was the first formal instantiation of a Turing Test.   The test is named after Alan Turing the British mathematician.  Alan Turing asked, “If a computer could think, how could we tell?” Turing’s suggested, that if the responses from the computer were indistinguishable from that of a human, the computer could be said to be thinking.

Along comes the year 1990,  Hugh Loebner and The Cambridge Center for Behavioral Studies decided to underwrite a contest designed to use the Turing Test. Dr. Loebner established a Grand Prize of $100,000 and a Gold Medal for the first computer whose answers were indistinguishable from a human’s.  Each year an annual prize of $2000 and a bronze medal is awarded to the closest human-like computer. No one has won the grand prize to date.

Do you think you could be confused by a computer?  Last years winner fooled 25% of the judges as stated by Discover Magazine.  Each judge ( all experts consisting of journalists, computer scientists, philosophy professors, and other academics) sits at a split computer screen.  One side is a human having a chat conversation with them, the other a robot doing the same.  They must declare which side is the human and which is the robot.

Not as easy as one would think.  One judge was fooled based purely on the responders location and lack of world news awareness.

Judge: So let’s cut straight to the point. Are you the human or the computer?

Respondent 1: What do you think?

Judge: That’s just the sort of answer I would expect from a computer.

R1: Well you could be wrong!!!

Judge: That’s true. It’s happened a lot in the past. What do you make of Sarah Palin?

R1: Sorry don’t know her

Judge: How can you possibly not know her? What have you been doing for the last two months?

The judge, a reporter, decided Respondant 1 was the robot, declaring the other screen was the human. In reality Respondent 1 was truly a French librarian who had never heard of Sarah Palin.

On the other hand robots also answered questions in ways that fooled judges.

Judge: I’d like to ask you some questions. What is going to solve this credit crisis?

Eugene: Damn! Are you going to ask me about all apparent things in the world? Read the “Encyclopedia for kinds”. I see you like being judge

How about this one

Judge: Hello

Ultra Hal: Good morning judge. Its 8-something [in the morning], so maybe you ate something. Get it?

Judge: Yes

The judge in this exchange chose the robot and said it was human.

So where does human intelligence and artificial intelligence begin and end.  Are we truly creating artificial intelligence or are we just extending our own?  The smarter and more technology savvy we become the smarter and more technology savvy our machines become. Ultimately, aren’t we the ones leading the race?  I mean, we are the ones creating the computers and programs…. aren’t we?

Kimberly Veautour

Acknowledgments:  Discover Magazine, Loebner.net

© 2010, Claws and Paws By Kymber. All rights reserved.