My key to LLM study has been to always primarily use a book and then let the LLM allow you to help with formulae, ask questions about the larger context, and verify your understanding.

Helping you parse notation, especially in new domains, is insanely valuable. I do a lot of applied math in statistics/ML, but when I open a physics book the notation and comfort with short hand is a real challenge (likewise I imagine the reverse is equally as annoying). Having an LLM on demand to instantly clear up notation is a massive speed boost.

Reading German Idealist philosophy requires an enormous amount of context. Being able to ask an LLM questions like "How much of this section of Mainländer is coming directly from Schopenhauer?" is a godsend in helping understand which parts of the writing a merely setting up what is already agreed upon vs laying new ground.

And the most important for self study: verifying your understanding. Backtracking because you misunderstood a fundamental concept is a huge time sync in self study. Now, every time I read a formula I can go through all of my intuitions and understanding about it, write them down, and verify. Even a "not quite..." from an LLM is enough to make me realize I need to spend more time on that section.

Books are still the highest density information source and best way to learn, but LLMs can do a lot to accelerate this.