I've decided that the main thing I'm building is my own mental model. You can take notes, create docs, put graphs and websites together, but unless I'm just trying to generate some reference material the only real objective is to develop the understanding and intuitions inside my own brain.
So I have the LLM offer a very short explanation of something, and from there's it's just me asking questions. Anything that feels fuzzy or not fully internalized is something I poke at until I'm satisfied.
It really has helped me develop a sensitivity to what I understand vs what I don't, and the ability to drill into any part of it is amazing.
I do this too. I use Claude. I picked a voice I like. I go on a three mile walk. I will ask it questions about a topic that I want to learn about. If it starts telling me more than I want to hear right then, I will say "stop". It doesn't get offended. I then ask it something else. I find this very effective. I control it so it only explains to me what I want explained. If what it says sparks questions on a related topic I jump to a brand new topic. No personal tutor could keep up with this or adjust to exactly how I want to be addressed like Claude does. I'm very excited about the progress I'm making mastering new topics.
And yes, it is not that it is just presenting the facts. By me taking control of the direction the questions and answers go, I can flesh out my mental model. I won't retain every little thing it tells me. But I am much farther ahead than before.
Can you say what topics you’re using this method to learn? I think it would be more effective for some than others.