logoalt Hacker News

corndogetoday at 2:54 AM5 repliesview on HN

There are many cases in which I already understand the code before it is written. In these cases AI writing the code is pure gain. I do not need to spend 30 minutes learning how to hold the bazel rule. I do not need to spend 30 minutes to write client boilerplate. List goes on. All broad claims about AI's effects on productivity have counterexamples. It is situational. I think most competent engineers quietly using AI understand this.


Replies

em-beetoday at 8:44 AM

In these cases AI writing the code is pure gain.

no, it isn't. unless the generated code is just a few lines long, and all you are doing is effectively autocompletion, you have to go through the generated code with a fine toothed comb to be sure it actually does what you think it should do and there are no typos. if you don't, you are fooling yourself.

solid_fueltoday at 7:30 AM

> There are many cases in which I already understand the code before it is written. In these cases AI writing the code is pure gain.

That's only true if the LLM understands the code in the same way you do - that is, it shares your expectations about architecture and structure. In my experience, once the architecture or design of an application diverges from the average path extracted from training data, performance seriously degrades.

You wind up with the LLM creating duplicate functions to do things that are already handled in code, or using different libraries than your code already does.

anileatedtoday at 8:29 AM

> There are many cases in which I already understand the code before it is written.

Typing speed is your bottleneck?

Analemma_today at 3:01 AM

The problem is, even if all that is true, it says very little about the distribution of AI-generated pull requests to GitHub projects. So far, from what I’ve seen, those are overwhelmingly not done by competent engineers, but by randos who just submit a massive pile of crap and expect you to hurry up and merge it already. It might be rational to auto-close all PRs on GitHub even if tons of engineers are quietly using AI to deliver value.

csomartoday at 3:07 AM

I mean we did copy/paste before this? Also create-react-app is basically that. And probably better than a stochastic AI generating it.