Nobody/Anonymous - 2004-10-25

Is there any possibility of getting the source for the amphetarate server?  I'm currently doing some research in collaborative filtering of news and I'd like to make use of Amphetarate or develop a similar system.  Also, I'd like to see better support for foreign languages.  I noticed that some foreign language items appear in my amphetarate feed.  I wonder how amphetarate deals with these; is there a separate learning mechanism for language preference, or it is just learned as part of the bayes/ACF learning?  I ask this because I'd like to be able to use a system like this for Japanese news items.