Generative AI is applied in different educational contexts such as essay writing or translation of texts. A specific application of generative models is creation of program code. Educators in schools and universities face the challenge how to assure that students acquire relevant competencies while making use of generative AI tools. In this paper, we present preliminary results of an online study of the use of code generators by Computer Science (CS) students. Beginner students get to learn basic programming concepts and skills, advanced students get to learn how to solve complex programming tasks and create programs which are correct, efficient, modifiable, and well documented. With the presented online study we want to explore which tasks students solve with code generators and with what purpose. 285 students participated in the survey, new beginners as well as advanced students, with the goal to compare students who learned programming basics without code generators with those who always had access to them. Preliminary results show that students are very eager to learn coding skills and want to understand underlying concepts. Students who struggle with coding skills tend to ask code generators more often for explanations and use code generators for the purpose of understanding. Students who chose not to use code generators are more skeptical of such systems and the mistakes they make. Our empirical results provide insights in how we can support students in acquiring coding skills while using code generators.