News for hackers. Stuff that matters.
Re:Ask HN: How to deal with shipping AI-written code you don... by i2km on Tuesday October 20, 2026 @12:43AM (#50161452)
What I don't understand is that for most SE jobs on mature codebases, writing code is maybe 5-10% of the work. And it's that 5-10% coding that keeps you 'grounded' in the code and keeps your tacit understanding up to date.

Get rid of that and you get a basically invisible productivity increase (call it 10% to be generous) but you've now lost tacit understanding. No amount of half-assed code review (or getting the LLM to generate "code quizzes" etc for you) is ever going to substitute for the tacit understanding you get from doing the 10% of coding yourself.

I really just don't get it. I mean, I can believe that using coding agents gives people a rush of power and fleeting illusions of increased productivity, but it's a mirage.

A lot of the comments here are trying to find some middle ground, i.e. trying to find some way to preserve tacit knowledge. But it seems to me that it's a waste of time. You either need to write the code yourself or completely give up on even reading or attempting to understand it. I just don't think there's any middle ground. Any well-intentioned attempt to preserve understanding of the code will fall afoul of human laziness and understanding drift

Re:Ask HN: How to deal with shipping AI-written code you don... by rewgs on Tuesday October 20, 2026 @02:07AM (#50161952)
I'm completely with you. It's baffling that this isn't totally self evident to devs everywhere.
Re:Ask HN: How to deal with shipping AI-written code you don... by DanielHB on Tuesday October 20, 2026 @05:21AM (#50163376)
You can keep tacit knowledge if you keep your prompts _really_ small and check the output at each step. That is how I write most of code these days, but I also interweave some manual editing occasionally (because it would be faster than prompting).

Basically using it as a way to type faster.

Re:Ask HN: How to deal with shipping AI-written code you don... by perlgeek on Tuesday October 20, 2026 @10:13AM (#50166795)
My attempts at finding a middle ground:

* I use LLMs to resolve the more annoying merge conflicts. It's not super hard work, but I don't like it, and I don't think I learn much from doing it.

* I implement a feature by hand, write some basic tests, and tell the AI to review it and write tests for cases that I missed (or was too lazy to do, most of the time)

* For 80% of the bugs that I fix, I have a pretty good idea going in where the bug might be. In the other cases, I ask the LLM to generate a list of hypotheses what's wrong. Often (but not always) it turns out one of the hypotheses was right.

* Sometimes it's not so easy to figure out how to trigger a bug in a test case. Haven't done it yet, but I plan to ask LLMs to experiment to try to do that for me.

* I use LLMs to generate tools that I wouldn't otherwise write (not high enough priority, too lazy, ...). For example, we had a rabbitmq connector that occasionally kept getting stuck without reconnecting in rare patterns of network interruptions. It wasn't really high priority for us (rare, easy to work around by restarting the service), so I didn't want to spend days of engineering on it. I asked Claude to write me a test harness that reproduced the issue, and it did. Having a bunch of automatically runnable scenarios made the actual fix not too hard.

* Sometimes, I have some software design problems where I feel I have a pretty good solution, but something about it feels off. Talking this through with an LLM often helps to refine or change the approach.

---

This approach to AI usage doesn't make me 10x more productive, but I do think it's a net benefit both for code quality and my enjoyment of the job. I don't know if, in a few months or years from now, I'll still be competitive like this, but right now, I'm doing fine.