The rapid development of artificial intelligence (AI) not only represents a scientific breakthrough but also has impacts on human society and economies, as well as on the development of economics. This paper focuses on the macroeconomic perspective, reviewing recent literature in order to answer three key questions. First, what approaches are being used to represent AI in economic models? Second, will AI technology have an impact on the economy different from that of previous new technologies? Third, in which aspects will AI have an impact, and what is the empirical evidence for these effects of AI?. On the first question, our review reveals that the incorporation of AI into economic models raises fundamental questions on economics and economic models. On the second question, while most empirical studies cannot deny the existence of the Solow Paradox for AI technology, some studies find that AI would have a different and broader impact than previous technologies. On the third question, studies on the labor market seem to suggest a stylized fact regarding the impact of AI on employment on different levels, and income inequality across skill levels and between developing and developed countries. The impacts of AI on international trade and education have been largely neglected and are worth further research in the future. It is also important for both theoretical and empirical studies to have a clear and accurate definition of AI so that the results are not misinterpreted.