Can AI Be Your Guide to the Web?
TrapIt has launched a beta website that recommends content, after learning your tastes, via an artificial-intelligence engine.
TrapIt’s technology has its roots in SRI’s DARPA-funded CALO project, designed to help computers understand the intentions of their human users (CALO also spun out Siri).
The user can select from existing “traps” — collections of articles related to featured or trending topics — and can create new traps by entering a few keywords and going through one screen of training data.
These change according to the user’s tastes alone — even if they were originally created by someone else. TrapIt’s algorithms comb through about 50,000 unique sources of content, analyzing articles to classify the types of information they contain. (The 50,000 sources were vetted by humans to filter out content farms and other material of dubious quality.) TrapIt combines this information with machine-learning analysis of what the user has previously clicked on to recommend new information.