Generative AI in Academics

There is a bifurcation in the academic voice regarding the adoption or rejection of generative AI in the classroom. This division in pedagogy remains ever present as educators struggle to catch up with advancing AI technology and its staunch integration into students everyday lives. A resounding concern from educators is for the authenticity of student work and the building of critical thinking skills, both of which become threatened by generative AI tools used without proper guidelines. Educators have a right to these concerns, as studies continue to show how generative AI tools successfully pass assessments and how the AI-coauthored work is challenging to detect or differentiate from student-authored work. In the field of Computer Science, the challenges compound as generative AI technology integrates seamlessly into already approved code-generation tools and development environments. Therefore, an informed and thoughtful decision must be made so that student learning can continue to flourish and evolve in a safe and inclusive setting. This research attempts to go beyond introductory course assessments, where a gap in research currently hangs. As curriculum becomes more challenging and abstract, can generative AI continue to pass assessments and be useful educational assistants? Or will these tools create more confusion for students as prompts become more advanced and prove difficult to interpret? During this empirical study, GitHub Copilot is assessed against the assessments of an advanced CS programming course. The findings present a resounding optimism for generative AI tools, with all assessments passed successfully. The study concludes with recommending an integrated approach of introducing and encouraging the use of generative AI. Collaboration with a partnership mindset will produce the best results.