Today's content providers are naturally distributed and produce large amounts of new information every day. Peer-to-peer information filtering is a promising approach that offers scalability, adaptivity to high dynamics, and failure resilience. The authors developed two approaches that utilize the Chord distributed hash table as the routing substrate, but one stresses retrieval effectiveness, whereas the other relaxes recall guarantees to achieve lower message traffic and thus better scalability. This article highlights the two approaches' main characteristics, presents the issues and trade-offs involved in their design, and compares them in terms of scalability, efficiency, and filtering effectiveness.