Classic clone detection approaches are hardly capable of finding redundant code that has been developed independently, i.e., is not the result of copy&paste. To automatically detect such functionally similar code of independent origin, we experimented with a dynamic detection approach that applies random testing to selected chunks of code similar to Jiang&Su's approach. We found that such an approach faces several limitations in its application to diverse Java systems. This paper details on our insights regarding these challenges of dynamic detection of functionally similar code fragments. Our findings support a substantiated discussion on detection approaches and serve as a starting point for future research.