thedreammachine

I've been naively assuming that most senior+ engineers were doing this too?

Is it mostly an artifact of the proof or does the algorithm actually need anything close to it?

I started with a curated backbone across several fields, drafted with frontier models and reviewed by hand. The automatic (and fun) part happens when you pick a goal and a quest gets generated with its own prerequisites, mapped onto that backbone.

It's def not as robust as Math Academy's graph yet, they spent years hand-building and testing it on real students. But I bet a few more iterations of frontier models get there, especially once there's learner data to correct it.