Human–AI Collaboration in Programming Education: Student Perspectives on LLM-Based Coding Assistants

The integration of large language models (LLMs) such as GitHub Copilot, ChatGPT, and DeepSeek into programming education has introduced a new form of human–AI collaboration. These tools provide real-time code suggestions, debugging assistance, and design support, yet their effects on learning, trust, productivity, and coding practices remain underexplored. We surveyed 248 students to examine relationships among these constructs, usage patterns by programming experience and academic level, the most frequently used assistants and programming languages, group differences in perceived learning and coding practices, and the extent to which learning, trust, and coding practices predict productivity. Students reported high adoption of ChatGPT and Python, generally positive perceptions of learning and productivity, and significant positive correlations among all constructs. Kruskal–Wallis tests indicated no significant differences in perceived learning across Basic, Intermediate, and Expert programmers, nor in coding practices across academic years (Years 1–4). Multiple regression showed that learning, trust, and coding practices jointly explained a substantial proportion of productivity variance (R2 = 0.628). These findings emphasize both opportunities and risks of AI integration and offer guidance for educators aiming to integrate AI tools while maintaining pedagogical rigor.