The Lazy Student's Dream: ChatGPT Passing an Engineering Course on Its Own

2025-02-23

AI Summary

This study investigates whether large language models (LLMs) can independently complete an undergraduate control systems course, rigorously evaluating their capability in mathematical derivation, Python programming, and control-theoretic reasoning under realistic student usage patterns. Method: Leveraging GPT-4–class models, the work implements an end-to-end evaluation of 115 authentic assignments—including multiple-choice questions, coding tasks, and theoretical analysis—under a “minimum-effort” protocol. Assessment integrates automated grading, expert human verification, multimodal task decomposition, and structured prompting strategies. Contribution/Results: The study introduces the first educationally grounded, course-level LLM competency framework, shifting AI-in-education paradigms from prohibition toward deep integration. Results show the model achieves an overall score of 82.24% (B-grade), closely matching the class average (84.99%). Performance excels on structured tasks but remains substantially limited on open-ended design problems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Analogy

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

This paper presents a comprehensive investigation into the capability of Large Language Models (LLMs) to successfully complete a semester-long undergraduate control systems course. Through evaluation of 115 course deliverables, we assess LLM performance using ChatGPT under a ``minimal effort"protocol that simulates realistic student usage patterns. The investigation employs a rigorous testing methodology across multiple assessment formats, from auto-graded multiple choice questions to complex Python programming tasks and long-form analytical writing. Our analysis provides quantitative insights into AI's strengths and limitations in handling mathematical formulations, coding challenges, and theoretical concepts in control systems engineering. The LLM achieved a B-grade performance (82.24%), approaching but not exceeding the class average (84.99%), with strongest results in structured assignments and greatest limitations in open-ended projects. The findings inform discussions about course design adaptation in response to AI advancement, moving beyond simple prohibition towards thoughtful integration of these tools in engineering education. Additional materials including syllabus, examination papers, design projects, and example responses can be found at the project website: https://gradegpt.github.io.

Problem

• Assessing ChatGPT's ability to complete an undergraduate control systems course.
• Evaluating AI performance in mathematical, coding, and theoretical engineering tasks.
• Exploring AI integration in engineering education beyond simple prohibition.

Innovation

• LLMs evaluated in control systems course
• ChatGPT tested with minimal effort protocol
• Quantitative analysis of AI in engineering education