"The aim is to create a system that can filter out aggressive and bullying tweets, delete spam, and allow normal tweets through"
It'll have to be a damned good system if it was to be relied on to censor people's feeds (whether they choose it or not).
I'd prefer to see it used to tag posts - sort of a 'public shaming'. If nothing else, they really need to put it out there in that form in order to get feedback on how well it is doing.
Perhaps El Reg could offer to be a guinea pig (when it moves beyond twitter) - offering up the comments sections on a few suitably contentious subjects.