Most software is fragile: even the slightest error, such as changing a single bit, can make it crash. As software complexity has increased, development techniques have kept pace to manage this fragility. But today there is a new challenge. Complexity is increasing rapidly as a result of two factors: the increasing use of distributed systems as a result of the sufficient reliability and bandwidth of the Internet, and the increasing scale of these systems as a result of the addition of many new computers to the Internet (e.g., mobile phones and other devices). To manage this new complexity, we propose an approach based on self-managing systems: systems that can maintain useful functionality despite changes in their environment. The talk motivates this approach and gives some ideas on how to build general self-managing software systems. An important part of the approach is to build systems as hierarchies of interacting feedback loops. We give examples of these systems and we deduce some rules of thumb for their design.