In this paper we discuss some fundamentals of “conventional” or “symbolic ” artificial intelligence (AI) and how connectionism, if done properly, can provide some genuinely novel aspects. We show some evidence against the traditional approach when viewed as a plausible model of animate intelligence. We also show that connectionist models appear to be much closer to an adequate model of “natural” behavior. Furthermore, we discuss possible impacts of connectionism on AI as afield of research and, beyond that, on how we think about our own mind. Many questions, however, remain open to permit a clear forecast of where the research will lead us.