|
|
|
|
|
by stripe_away
290 days ago
|
|
and to be blunt, I learned similar things building analog synths, before the dawn of LLMs. Like you, I don't like watching videos. However, the web also has text, the same text used to train the LLMs that you used. > When something doesn't work like I thought it would, AI helps me understand where I may have went wrong, I ask it a ton of questions, and I try again until I understand how it works and how to prove it. Likewise, but I would have to ask either the real world or written docs. I'm glad you've found a way to learn with LLMs. Just remember that people have been learning without LLMs for a long time, and it is not at all clear that LLMs are a better way to learn than other methods. |
|
I think the problem was all of the getting started guides didn't really solve problems I cared about, they're just like "see, a light! isn't that neat?" and then I get bored and impatient and don't internalize anything. The textbooks had theory but so much of it I would forget most of it before I could use it and actually learn. Then when I tried to build something actually interesting to me, I didn't actually understand the fundamentals, it always fails, Google doesn't help me find out why because it could be a million things and no human in my life understands this stuff either, so I would just go back to software.
It could be LLMs are at least possibly better for certain people to learn certain things in certain situations.