What is the solution? Toss out thousands of years of tested pedagogy which shows that most people learn by trying things, asking questions, and working through problems with assistance and instead tell everyone to read a textbook by themselves and learn through osmosis?

So what if the LLM is wrong about something. Human teachers are wrong about things, you are wrong about things, I am wrong about things. We figure it out when it doesn't work the way we thought and adjust our thinking. We aren't learning how to operate experimental nuclear reactors here, where messing up results in half a country getting irradiated. We are learning things for fun, hobbies, and self-betterment.

>we aren't at a level where a LLM can truly be relied upon to teach topics across the board.

You can replace "LLM" here with "human" and it remains true.

Anyone who has gone to post-secondary has had a teacher that relied on outdated information, or filled in gaps with their own theories, etc. Dealing with that is a large portion of what "learning" is.

I'm not convinced about the efficacy of LLMs in teaching/studying. But it's foolish to think that humans don't suffer from the same reliability issue as LLMs, at least to a similar degree.

Sure, humans aren't without flaws in this area. However, in real time, humans can learn and correct themselves, we can check eachother, ask for input, etc, and not continue to make mistakes. This isn't the case with LLMs as a service.

For example, even if you craft the most detailed cursor rules, hooks, whatever, they will still repeatedly fuck up. They can't even follow a style guide. They can be informed, but not corrected.

Those are coding errors, and the general "hiccups" that these models experience all the time are on another level. The hallucinations, sycophancy, reward hacking, etc can be hilariously inept.

IMO, that should inform you enough to not trust these services (as they exist today) in explaining concepts to you that you have no idea about.

If you are so certain you are okay to trust these things, you should evaluate every assertion it makes for, say, 40 hours of use, and count the error rate. I would say it is above 30%, in my experience of using language models day to day. And that is with applied tasks they are considered "good" at.

If you are okay with learning new topics where even 10% of the instruction is wrong, have fun.