logoalt Hacker News

beej71 • today at 3:18 PM • 3 replies • view on HN

One thing to keep in mind is that anytime you punt to the LLM (or anybody) for anything, that skill is going to atrophy.

I've seen this happen to myself where suddenly I had trouble planning out the architecture for a very small project. It should have been obvious to me, and I knew that. So it was disconcerting to not be able to suddenly have the answer appear in front of me like it normally would. I thought maybe I would go to Claude and help get some ideas.

But then I stopped myself. I knew I should be able to do this! So I got out a piece of paper and I scribbled ideas until the dam burst and suddenly the entire design was obvious, like it should have been in the first place. It took about 5 minutes.

But those were an alarming 5 minutes. It was like I'd gone blind to the solution.

And I realized that when I asked Claude for a bunch of ideas and then I selected the best one based on my experience, I was exercising that exact skill. I wasn't exercising the skill of coming up with the solution from scratch.

Lots of times we're happy letting particular skills atrophy. Maybe we don't like exercising them and we just don't want to do that anymore. And I think that's valid.

Just be careful how you use it.


Replies

pton_xd • today at 3:34 PM

5 minutes... what about 5 hours, or 5 days? Imagine spending 5 hours with a pen and paper sketching solutions. Unthinkable to spend that amount of time "unproductively" today. I feel like there's just so much pressure to make visible progress, and with these tools available it's getting harder to convince yourself to take the time to think.

➕ show 2 replies
seanmcdirmid • today at 9:57 PM

It’s not just that, punting something to an LLM is its own skill that will push out the other skills you were using to do everything on your own. It’s like going from an IC to a tech lead manager, you go from doing things on your own to figuring out how to get a team (of agents) to do it instead.

dylanhouli • today at 7:54 PM

This is why I like to come up with my own solution(s) for a problem first, and then ask AI what it recommends to see if we match up. Makes it a fun exercise, and usually ends up helping creating one ideal, combined idea.