Group size covaries with relative neocortical volume in nonhuman primates. This regression equation predicts a group size for modern humans very similar to that for hunter-gatherer and traditional horticulturalist societies. Similar group sizes are found in other contemporary and historical societies. Nonhuman primates maintain group cohesion through social grooming; among the Old World monkeys and apes, social grooming time is linearly related to group size. Maintaining stability of human-sized groups by grooming alone would make intolerable time demands. It is therefore suggested (1) that the evolution of large groups in the human lineage depended on developing a more efficient method for time-sharing the processes of social bonding and (2) that language uniquely fulfills this requirement. Data on the size of conversational and other small interacting groups of humans accord with the predicted relative efficiency of conversation compared to grooming as a bonding process. In human conversations about 60% of time is spent gossiping about relationships and personal experiences. Language may accordingly have evolved to allow individuals to learn about the behavioural characteristics of other group members more rapidly than was feasible by direct observation alone.