Search
On-Site Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
Search Tips
Change Preferences / Time Zone
Sign In
Bluesky
Threads
X (Twitter)
YouTube
Productive Failure (PF) involves students attempting challenging problems before direct instruction to deepen learning, but creating these problems is time-consuming for educators. This study explores using ChatGPT 4o to create Algebra problems. We developed a rubric to assess PF problems and tested ChatGPT 4o’s effectiveness in assessing and generating these problems. Second, we trained ChatGPT 4o to assess and generate Algebra problems. Finally, we conducted a pilot study to compare the ratings of problems by human experts and ChatGPT 4o. In parallel, we prompt-engineered ChatGPT 4o and generated 30 Algebra items. The results showed high correlation between human and AI assessments of problem quality. Also, we found that on average ChatGPT 4o can generate high quality Algebra problems.