We study the instability of hyper-specialization of exports. We have two main findings. (1) Specializations are surprisingly unstable: Export ranks are not persistent, and new top products and destinations replace old ones. Measurement error is unlikely to be the main or only determinant of this pattern. (2) Source-country factors are not the main explanation of this instability: Only 20% of the variation in export growth can be explained by variation in comparative advantage (source-by-product factors), while another 20% of the variation in export growth can be explained by variation in bilateral (source-by-destination) factors.