This social/hall would aim to bring people together to discuss the interesting open problems in the domain of decentralized AI (and related fields like private ML, federatd learning etc.) and to look for more opportunities to work together. We would aim to faciliate informal sharing of (1) recent work and results, and (2) proposal of collective action; the overal focus would be on how we can better mobilize to lift the quality and quantity of research in this area. Additional topics of interest include: improved benchmarks, realistic datasets and advancing the common understanding of what are the most important settings for decentralized AI to tackle? The primary hosts would be Flower which is the most popular open-source framework for federated and decentralized AI and academics from the University of Cambridge. If accepted we would also attempt to invite other interested parties to attend to add more life to the proceedings.