Hard-coding explanations feels tedious, takes a lot of work, and isn’t “sexy” like an AI that generates responses from scratch – but at least it’s not a pipe dream. It’s a practical solution that lets you move on to other components of the AI that are just as important.
Want to get notified about new posts? Join the mailing list and follow on X/Twitter.
Many people who have (unsuccessfully) attempted to apply AI to education have focused too much on the “explanation” part and not enough on scaffolding, navigating, and managing the entire learning process. It’s easy to go on a wild goose chase building an explanation AI.
You fall in love with the idea of AI having conversational dialogue with students, and then you get lost in the weeds of complexity. You solve just enough of the problem to produce a cool demo, yet you’re still hopelessly far away from self-service learning in real life.
Dialogue isn’t even necessary. You can just hardcode explanations into bite-size pieces, served at just the right moment. And you can close the feedback loop by having students solve problems, which they need to do anyway. (Their “response” is whether they got it correct.)
Moreover, if you hard-code the content and analyze student performance data, then it’s easy to continually detect and further scaffold any areas where more than a sliver of students struggle to solve problems correctly. You don’t need a million halfway decent explanations. What you need is a single great explanation that’s been repeatedly battle-tested, analyzed, and refined across a large number of students. (more)
Sure, hard-coding explanations feels tedious, takes a lot of work, and isn’t “sexy” like an AI that generates responses from scratch – but at least it’s not a pipe dream. It’s a practical solution that lets you move on to other components of the AI that are just as important.
What are those other components? A handful off the top of my head:
- After a minimum effective dose of explanation, the AI needs to switch over to active problem-solving. Students should begin with simple cases and then climb up the ladder of difficulty, covering all cases that they could reasonably be expected to solve on a future assessment.
- Assessments should be frequent and broad in coverage, and students should be assigned personalized remedial reviews based on what they answered incorrectly.
- Students should progress through the curriculum in a personalized mastery-based manner, only being presented with new topics when they have (as individuals, not just as a group) demonstrated mastery of the prerequisite material.
- After a student has learned a topic, they should periodically review it using spaced repetition, a systematic way of reviewing previously-learned material to retain it indefinitely into the future.
- If a student ever struggles, the system should not lower the bar for success on the learning task (e.g., by giving away hints). Rather, it should strengthen a student’s area of weakness so that they can clear the bar fully and independently on their next attempt.
Want to get notified about new posts? Join the mailing list and follow on X/Twitter.