Physics on autopilot: exploring the use of an AI assistant for independent problem-solving practice

Abstract

This study investigates the efficacy of large language model (LLM)-powered chatbots in guiding physics problem-solving, examining whether they can effectively supplement teacher-led learning. A customised chatbot was developed leveraging ChatGPT to provide step-by-step assistance through a structured problem-solving algorithm. Its impact was evaluated via an experimental study with 12th-grade physics students (N = 24) randomly assigned to a teacher-guided or chatbot-guided group for problem-solving practice. A Mann-Whitney U test revealed no significant differences in problem-solving competency between conditions. Qualitative analysis of conversational logs indicates the chatbot successfully emulated key teacher scaffolding behaviours. Our findings suggest AI tutors can deliver personalised, interactive support akin to human teachers, offering viable supplements to augment physics learning. Further research should explore optimising LLM training, human-chatbot balances, and impacts across diverse educational settings.

Trends and challenges in implementing media education in Ukraine

“…There is a tendency for people to be replaced by artificial intelligence in many areas of their activity. Neural networks, which are able not just to communicate with a person, answering questions, but to joke in response and even anticipate the continuation of the dialogue; works of art created by artificial intelligence, cars with complete autopilot -all these factors become a reality that cannot be ignored [31,39]. In the future, all the physical capabilities of a man can be replaced by a robot.…”