Learn Your Way: Reimagining Textbooks with Generative AI

I looked at the example for computer science basics for a 7th grader interested in food. Explanations include:

"a list can be used for a recipe"

"a set can be used to list all the unique ingredients you need to buy for a week's meals"

"a map can be used for a cookbook"

"a priority queue can be used to manage orders in a busy restaurant kitchen"

"a food-pairing graph can show which ingredients taste good together"

Maybe I'm over-estimating the taste of 7th graders, but I feel like I would get sick of this really quickly.

I'm sure computer science has improved in high school over the last (gulp) 20 years, but when I did variations of IT and programming lessons before university, it was bad. This was peak "you must Microsoft Office"-era. I've been involved in outreach for almost as long at this point. A lot of kids ask sensible questions like 'when do I ever need to use trig in real life?', because the examples in lessons and exams are so divorced from reality that it feels pointless.

I do think there is pedagogical value in showing where these concepts can be used practically and the advantage of LLMs is that you can transform the examples to what you're actually interested in. For example the Red Blob Games series on A* pathfinding are really good at showing how Dijkstra and graph traversal algorithms work, for a use-case (video games) that is appealing to a lot of nerdy people.