The paper describes a system of belief representation in which inner, nested, beliefs (what an individual A believes an individual B believes about C are not normally shared permanently with the component belief sets (e.g., the system's view of A, etc.). It is argued that this process is consistent with a general Least Effort Theory of Understanding, and that any assumption that such nested beliefs are already shared and computed, awaiting access, is implausible. This view is also contrasted with a theory of relevance of Sperber and Wilson which claims that dialogue inferences can be computed without the need to separate, or nest, sets of beliefs corresponding to distinct individuals.