Bright key facts / Demonstrated
When the answer arrives too soon.
A preregistered randomized trial in a Turkish high school compared a standard GPT-4 chat interface, a teacher-informed GPT tutor with guardrails, and no generative-AI resource during mathematics study sessions.
- AI’s role
- The study compared GPT-4 assistance that resembled ordinary chat with a version whose prompts and boundaries were designed with teacher input to support learning.
- Documented result
- The paper's preregistered primary analysis of unassisted exams found that generative AI without guardrails could harm learning. The teacher-informed guardrailed tutor largely mitigated that negative effect.
- Important limitation
- The study examined short-term exam outcomes in one high-school mathematics setting.