Programming skills are typically developed through completing various hands-on exercises. Such programming problems can be contextualized to students’ interests and cultural backgrounds. Prior research in educational psychology has demonstrated that context personalization of exercises tickles learners’ situational interests and positively affects their engagement. However, creating a varied and comprehensive set of programming exercises for students to practice is a time-consuming and laborious task for computer science educators. Previous studies have shown that large language models can generate conceptually and contextually relevant programming exercises. Thus, they offer a possibility to automatically produce personalized programming problems to fit students’ interests and needs. This article reports on a user study conducted in an introductory programming course that includes contextually personalized programming exercises created with GPT-4. The quality of the exercises is evaluated by both students and the authors. Additionally, this work investigates student attitudes towards the created exercises and engagement with the system. The results suggest that the quality of exercises generated by GPT-4 is generally high according to both students and the authors, and that they are very well received by students. This suggests that AI-generated programming exercises can be a good addition to introductory programming courses to provide students a practically unlimited pool of exercises targeting both their interests and concepts on which they would benefit from additional practice.