Task switching is an important executive function, and finding ways to improve it has become a major goal of contemporary scientists. Karbach and Kray (2009) found that training in the Alternating-Runs Task-Switching (AR-TS) paradigm (in which the task changed every second trial) reduced the costs of switching in untrained tasks, as well as led to far transfer to interference control ability and fluid intelligence. However, AR-TS is known to involve working memory updating (WMU). Therefore, we hypothesized that AR-TS training involves WMU and not task-switching proper. Participants were trained using Karbach and Kray's protocol. Results indicate a highly specific transfer pattern in which participants showed near transfer to switching cost in the AR-TS paradigm, but did not significantly improve in another version of the task switching paradigm in which the tasks were randomly ordered or a version in which the task changed every 3rd trial. The results suggest that what has been trained is not a broad task-switching ability but rather a specific skill related to the unique WMU requirements of the training paradigm.