In a recent test of 2000 users, nanniebots did such a good job of imitating child users that none could distinguish whether it was a bot chatting with them or a real user.
The Turing Test refers to the test for whether or not a machine has succeeded at Artificial Intelligence. From The Turing Test Page I quote:
When talking about the Turing Test today what is generally understood is the following: The interrogator is connected to one person and one machine via a terminal, therefore can't see her counterparts. Her task is to find out which of the two candidates is the machine, and which is the human only by asking them questions. If the machine can "fool" the interrogator, it is intelligent.
Perhaps a formal test approach should be taken to test this new software. Isn't there a prize involved?
No comments:
Post a Comment