Modern programming tools use generative AI (GenAI) to suggest code to the user as they type, which can interrupt a novice’s problem-solving behavior and undermine the development of their programming critical thinking skills. In this paper, we present a scaffolded programming exercise designed to support student differentiation between good and bad GenAI code suggestions based on negative expertise–that identifying why an answer is wrong is part of developing conceptual knowledge. We compare two different variations of the tool that showed either only one suggestion or showed multiple suggestions. Our results show that students performed better in the single suggestion condition than in the multiple suggestions condition. Despite this, 68% of students wrote in their post-test reflections that they preferred the multiple suggestion condition because it made them slow down and think critically about the line under consideration, the overall purpose of the code, and the benefits of planning.