A major problem with using LLMs to learn things:
Me: "A is true, therefore B is false, right?"
LLM: "Right! Here's a ton of detail to confirm your belief."
Me: "Actually, A is false; B is true."
LLM: "Exactly right! Here's more detail to confirm that belief."
