and then you verify every single fact it tells you via traditional methods by confirming them in human-written documents, right?
Otherwise, how do you use the LLM for learning? If you don't know the answer to what you're asking, you can't tell if it's lying. It also can't tell if it's lying, so you can't ask it.
If you have to look up every fact it outputs after it does, using traditional methods, why not skip to just looking things up the old fashioned way and save time?
Occasionally an LLM helps me surface unknown keywords that make traditional searches easier, but they can't teach anything because they don't know anything. They can imagine things you might be able to learn from a real authority, but that's it. That can be useful! But it's not useful for learning alone.
And if you're not verifying literally everything an LLM tells you.. are you sure you're learning anything real?