"Give me the code" -- Log Analysis of First-Year CS Students' Interactions With GPT

TL;DR

This study analyzes how first-year CS students interact with GPT for coding tasks, revealing their ability to use AI tools effectively and exercise judgment, despite minimal prompt training.

Contribution

It provides insights into students' prompt usage and critical thinking development when using GPT without prior prompt training in a CS education context.

Findings

Most students successfully used GPT-generated solutions.

Half of the students demonstrated critical evaluation skills.

Students incorporated AI solutions into their projects effectively.

Abstract

The impact of Large Language Models (LLMs) like GPT-3, GPT-4, and Bard in computer science (CS) education is expected to be profound. Students now have the power to generate code solutions for a wide array of programming assignments. For first-year students, this may be particularly problematic since the foundational skills are still in development and an over-reliance on generative AI tools can hinder their ability to grasp essential programming concepts. This paper analyzes the prompts used by 69 freshmen undergraduate students to solve a certain programming problem within a project assignment, without giving them prior prompt training. We also present the rules of the exercise that motivated the prompts, designed to foster critical thinking skills during the interaction. Despite using unsophisticated prompting techniques, our findings suggest that the majority of students successfully leveraged GPT, incorporating the suggested solutions into their projects. Additionally, half of the students demonstrated the ability to exercise judgment in selecting from multiple GPT-generated solutions, showcasing the development of their critical thinking skills in evaluating AI-generated code.