EMU math department blog

Last semester I wrote about Emacs Psychiatrist, a cute computer program that tries to have “intelligent” conversations with the user. If you talk to the program for several minutes, you quickly discover that it is not so intelligent. Can a more complicated computer program behave better? In computer science we use Turing test to test weather a computer program achieved any intelligence. The idea is very simple—if you cannot tell what a computer program produces from what a human produces, then we say this computer program achieved a certain level of human intelligence.

Here is a toy Turing test I got from www.cs4fn.org. One of the following two sentences is produced by a computer program. Can you tell which one it is?

1. What’s fast and wiry?… An aircraft hanger!
2. What’s green and bounces?… A spring cabbage!

You can follow any responses to this entry through the RSS 2.0 feed. Responses are currently closed, but you can trackback from your own site.