Generative artificial intelligence (AI) has shown potential in solving physics problems1,2 and providing feedback on assessments.3 However, results sometimes still are inaccurate4 or at the wrong level, or use notations and definitions not appropriate for a particular course. A possible solution is augmenting the prompts with course-specific reference materials. Also, for feedback on homework solutions and grading exams, the problem text and the sample solution or grading rubric can be injected into the prompts.5 Project Ethel at ETH Zurich aims to construct a virtual teaching assistant using these practices.
© 2001-2025 Fundación Dialnet · Todos los derechos reservados