Commentary: Distributed Cognition and Distributed Morality: Agency, Artifacts and Systems

Studies on human-artifact interaction stimulate reflection on the bounds of cognition, agency, and even morality (e.g., Floridi and Sanders, 2004). Heersmink (2017) compares distributed cognition (DCog) and distributedmorality theory and claims that some artifacts, depending on their use, have cognitive and moral status but lack cognitive and moral agency. According to him, an extended cognitive system (ECS) has agency when artifact(s) included in the system are fully transparent and densely integrated into the cognitive processes of the user, whereas a distributed cognitive system (DCS) without central control lacks agency. My doubts do not concern Heersmink's main claim. Irrespective of the final assessment of the moral status of distributed systems, I argue that the assumption that the assessment of the degree to which humans and artifacts are cognitively integrated is not always feasible and distorts our understanding of DCog.