Generative AI (GenAI), in particular large language models (LLMs), have rapidly become part of software engineers’ toolboxes. While the software engineering community has actively debated efficacy and extent of use of GenAI tools, little is known about how early- career developers apply these tools and transfer their classroom training into practice. To address this gap, we conducted a con- trolled study with graduate students in a top-tier Master of Software Engineering program who were enrolled in a software refactoring course. The study compared how students solved a library upgrade problem using an ad hoc non-LLM approach versus an automated approach supported by LLMs. Our findings show that students of- ten failed to apply disciplined software engineering practices when relying on LLMs, simply feeding them error text from builds rather than using them to understand issues and explore solutions. Our results highlight a dual challenge for educators: reinforcing foun- dational software engineering skills and their transfer to GenAI use, while also introducing new competencies such as effective prompting and navigating LLM-driven workflows.