Hacker News Reader

Comment by nightwalkerkg | Hacker News Reader

My main issue with using AI as a learning platform is that unlike documentation, books, Youtube videos, there is not really a process of having someone "review the learning material". For example, I can always read the review of some book or ciriculum, the comments under a video, or if it's some for of open source documentation you can check the PRs and verify to some extent it's claim. With AI I can't really say what it has halucinated, because I am learning a new thing, I don't have that benefit of previously reviewed material.

View on HN

This is (exactly) why I very strongly tell people not to teach themselves with an LLM. Particularly from the ground up. If you do not understand the domain, you cannot learn from the model because you won't know what questions to ask and it certainly isn't going to answer all of them for you.

The LLM doesn't have to be the sole single only exclusive source you learn from. It's an addition to a mix. Nothing is a single definitive answer. Same way as many other things, like Anki flashcards or Duolingo or some YouTube channel, or some tutorial website or indeed a coursebook or an audio course or whatnot. Use multiple sources and use the strengths of each.

What you describe is indeed the ideal method of learning. However, I think we both know that if LLMs are pushed as a learning device, people will substitute everything else for them (or companies will very strongly encourage that substitution).

You can ask the LLM to connect the dots to the sources before displaying it to you so you can see the proof in line.

You can ask the LLM how to do this. Start with a topic you know well to get the mechanism working and trust it well.

Of course, and that is what I do, but it becomes and additional mental and time consuming effort. As an dumb example, if I am learning a new programming language and trying to grasp some concept, I'll check the docs, find the section and read it. I trust that the source in the docs has been already vetted by other devs and the authors. But if I ask the AI the same thing, I then need to verify it's claims usually by asking it to check if the info is true, and then possibly opening the source link (lucky for me Claude provides the links in the desktop app as footnotes). It's not a question about AI, it's about the trust I have of this tool, it builds over time, but as soon as the AI makes an assumption or a hallucination we are back down to square one.

I assume this will become less of an issue in the future as there is more trust between the AI tools and me.

Reply on news.ycombinator.com