Jon Udells Investigating A Bayesian RSS Categorizer Bayesian S

Jon Udell’s investigating a Bayesian RSS categorizer. Bayesian spamfilters correlate the probability of words (such as “v1agra” or “ontology”) appearing in an email message; if the aggregate probability from all the words in an email exceeds a certain threshold, the email is put in a specific folder. The blog correlary (I think) would be analyzing RSS items as to whether they’re deleted, opened, and opened-and-clicked-through; over time, such a system should be able to assign a probability to the likelihood that a new RSS item will be of interest to you (and presumably you’d sort by that in your aggregator). 

Jon appears to be doing something dangerously more ambitious, which is creating a Bayesian categorizer that assigns Jon-meaningful categories (email, collaboration, family, etc.) to items. I say “dangerously more ambitious” because Jon’s approach would seem to require a lot of supervision, while the genius of Bayesian spam-filtering is that pressing a button marked “Delete as spam” is no more onerous than deleting the spam in the first place. Similarly, a Bayesian RSS aggregator that just attempted to categorize “Will this item be read, will this item be clicked-through, will this item be deleted without pause?” requires no more supervision than what is natural to the task of RSS browsing.

Difference between graphics and ink blogging

I have no idea of the capabilities of Microsoft’s ink blogging tools, but IMO the real ink blogging solution will be one that stores ink on the server and returns ink if the client sends up an appropriate MIME type. Only if the client is incapable of rendering ink will it downgrade the ink to graphics + text (which, of course, the server might cache). Until that capability becomes available, ink on the Web is just a toy.

Peter Rysavys Lonestar Screenshots And Discussion Microsoft Handed Ou

Peter Rysavy’s Lonestar screenshots and discussion: Microsoft handed out Lonestar alphas at the Tablet PC get-together at Comdex. Oh man, I should have listened to that little voice in my head that told me to go to Vegas. Most interestingly, Peter says that Lonestar is a small (~10MB), user-installable and uninstallable upgrade that runs absolutely fine on first-generation hardwares. Essentially, it sounds like a case where resource tradeoffs had resulted in more effort on OS and hardware foundations for the release of XP Tablet edition 1.0 and that Longhorn is the result of a significant amount of those resources shifting towards handwriting and user-experience. Plus, it stands to reason that the number of people with a deep, low-level understanding of the Tablet OS has increased hugely over the past year, so it’s not surprising that there could be, for instance, significant improvements in handwriting recognition on existing hardware.