Miller comments on Open Thread, January 2011 - Less Wrong

4 Post author: ciphergoth 10 January 2011 11:14AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (42)

You are viewing a single comment's thread. Show more comments above.

Comment author: Miller 16 January 2011 08:19:53PM *  1 point [-]

Watson apparently refines it's notion of the kinds of answers that are expected under a given category as it accumulates previous answers. The human contestants could exploit this by starting with the higher dollar questions. I'll be curious to see if they do.

There's a detailed chart of the performance over time of the system here.