alt Hacker News> Perhaps you’re a user of LLMs. I get it, they’re neat tools. They’re useful for certain kinds of learning. But I might suggest resisting the temptation to use them for projects like this. Knowledge is not supposed to be fed to you on a plate.
I get where this is coming from, and I even agree with it today, but I also want to tag it as "don't cache this opinion too hard". It's interesting to notice when and how our advice for getting help from AI is different from our advice for getting help from other humans. It would be kind of odd, wouldn't it, to put a paragraph at the bottom of a blog post that said "by the way if you have friends who are expert programmers, I don't recommend asking them for help." I think there are two clear reasons that feels odd: 1) expert friends can actually answer your questions and get you personally unstuck, which is huge, and 2) expert friends usually understand why you're doing what you're doing and that they're supposed to help do it yourself instead of just doing it for you.
One thing I bet few people have tried (because I haven't tried it myself) is actually asking an LLM to guide you like an expert friend would, instead of just spitting out code to solve your problem. Maybe they're bad at that, I wouldn't be surprised. But if so, I bet in a year or two they'll be amazing at it. It might be good to build the habit of clarifying what sort of help you need, instead of assuming an LLM will give you the wrong kind of help?
Replies
> "by the way if you have friends who are expert programmers, I don't recommend asking them for help."
AI is not an expert programmer [today]. and it doesnt take an expert programmer to arrive at that conclusion.
This is by far my most common usage of LLMs, and they’re good at it. Sometimes you have to be intentional about preventing it from being sycophantic and just telling you that you’re right, through a system prompt or by phrasing the question such that it’s comparing ideas neutrally instead of comparing “your” idea to some other idea.
It feels like Claude and ChatGPT have both become more sycophantic over the past months.
I try to do exactly that. I phrase it as using LLM as teachers instead of interns.
(I'm the post author) Actually, I would recommend that you don't ask an expert friend for help. If you get really stuck then maybe do some light reading about the topic: but the point is to throw lots of things at the wall and puzzle your way through it. Figuring things out from first principles is fun and also provides you with a litany of creative thinking skills to help you tackle other problems. I firmly believe that spending time confused is an essential ingredient in the process.
Obviously, you're welcome to do as you please though, mileage may vary, etc.