> However, our system relies on frontier LLMs, whose compute costs still remain nontrivial. Moreover, each textbook was formalized in isolation, without the careful planning needed to make it maximally compatible with existing mathlib infrastructure. Human involvement currently remains necessary to handle such organisational concerns — selecting and ordering books in a dependency-aware manner, bridging mismatched conventions across sources, etc
> However, our system relies on frontier LLMs, whose compute costs still remain nontrivial. Moreover, each textbook was formalized in isolation, without the careful planning needed to make it maximally compatible with existing mathlib infrastructure. Human involvement currently remains necessary to handle such organisational concerns — selecting and ordering books in a dependency-aware manner, bridging mismatched conventions across sources, etc