> cognitive friction is the engine of learning. I agree 100% too.

This is why in order to understand new codebase or to ramp up to new projects, I use AI to generate a textbook style reading material for me along with "verify yourself" types of exercises along the way. Then I print them on a paper and read it using a pencil/pen and take notes.

Because of my math training, I am in the habit of slowing down to read textbook style texts which helps.

> I use AI to generate a textbook style reading material for me along with "verify yourself" types of exercises along the way

This is fascinating. Any chance you have your workflow or prompts documented and would be willing to share them?

Exactly the type of usage I would hope to see advocated for in the future. As I wrote, when leveraged with Socratic methods and a sort of "interactive documentation", they can really boost one's understanding. Of course, this is predicated on the individual having enough information to know the right questions to ask.

I also do this. It would be better I think to generate exact references to primary and canonical sources to avoid learning LLMisms, or to feed it these and have it ensure its material is anchored to those good references.