ChatGPT-4 with Code Interpreter can be used to solve introductory college-level vector calculus and electromagnetism problems
This addresses the problem of AI assistance in solving introductory engineering-math problems for students and instructors, but it is incremental as it builds on existing models with a new tool.
The study evaluated ChatGPT-4 with Code Interpreter on 13 college-level vector calculus and electromagnetism problems, finding it solved most problems satisfactorily most of the time, a major improvement over versions without Code Interpreter.
We evaluated ChatGPT 3.5, 4, and 4 with Code Interpreter on a set of college-level engineering-math and electromagnetism problems, such as those often given to sophomore electrical engineering majors. We selected a set of 13 problems, and had ChatGPT solve them multiple times, using a fresh instance (chat) each time. We found that ChatGPT-4 with Code Interpreter was able to satisfactorily solve most problems we tested most of the time -- a major improvement over the performance of ChatGPT-4 (or 3.5) without Code Interpreter. The performance of ChatGPT was observed to be somewhat stochastic, and we found that solving the same problem N times in new ChatGPT instances and taking the most-common answer was an effective strategy. Based on our findings and observations, we provide some recommendations for instructors and students of classes at this level.