AI Agents and the Refactoring That Never Happens • Hacker News Board

Re: AI Agents and the Refactoring That Never Happens

#61

Post by rosenfeld » Thu, Sep 03, 2026, 1:28 AM UTC

jdkoeck wrote: post #39

This is obviously written by an LLM. Should we flag such content?

Did I even tried to pretend the article wasn't generated with Claude's help?

I even shared the initial prompt in some comment in this thread. I don't understand what is the matter with also using AI help with generating articles. I still reviewed the article and put all the ideas I wanted to discuss in that article. I don't see why people are often complaining about this. The article content is much more important than how it was generated.

Re: AI Agents and the Refactoring That Never Happens

#62

Post by jing09928 » Thu, Sep 03, 2026, 1:35 AM UTC

[dead]

Re: AI Agents and the Refactoring That Never Happens

#63

Post by kyleee » Thu, Sep 03, 2026, 2:08 AM UTC

Sivart13 wrote: post #53

teaearlgraycold wrote: post #49

Earlier quoted context omitted.

Not sure what you’re getting at

Test coverage for its own sake is not always a worthwhile goal.

Unless it was indeed valid coverage? You are assuming it was all bad

Re: AI Agents and the Refactoring That Never Happens

#64

Post by deterministic » Thu, Sep 03, 2026, 5:10 AM UTC

Not my experience at all. Quite the opposite. At my workplace we use AI to improve code quality and software design every day, far more than we used to, because AI makes it fast and easy.

Re: AI Agents and the Refactoring That Never Happens

#65

Post by nottorp » Thu, Sep 03, 2026, 7:34 AM UTC

teaearlgraycold wrote: post #49

nottorp wrote: post #26

Earlier quoted context omitted.

> then had a commit made for every minor issue found Interesting choice of words. Not a fix. Not a refactor. A commit.

Not sure what you’re getting at

That's how the LLMs made you think of your work? You're producing commits now?

It's like "content creator" vs "writer" or "artist".

Re: AI Agents and the Refactoring That Never Happens

#66

Post by teaearlgraycold » Thu, Sep 03, 2026, 8:13 AM UTC

Sivart13 wrote: post #53

teaearlgraycold wrote: post #49

Earlier quoted context omitted.

Not sure what you’re getting at

Test coverage for its own sake is not always a worthwhile goal.

Coverage started out kind of mediocre, about 50% IIRC. There were a lot of easy wins, and a handful of files were intentionally ignored.

I also had it first review all tests for superfluous ones that could be deleted.

Re: AI Agents and the Refactoring That Never Happens

#67

Post by teaearlgraycold » Thu, Sep 03, 2026, 8:17 AM UTC

nottorp wrote: post #65

teaearlgraycold wrote: post #49

Earlier quoted context omitted.

Not sure what you’re getting at

That's how the LLMs made you think of your work? You're producing commits now? It's like "content creator" vs "writer" or "artist".

I'm not producing commits. LLMs are producing commits.

Fix more things, solve more problems, and do it to a higher degree of quality in less time using LLMs. What's to complain about?

Re: AI Agents and the Refactoring That Never Happens

#68

Post by nottorp » Thu, Sep 03, 2026, 9:08 AM UTC

teaearlgraycold wrote: post #67

nottorp wrote: post #65

Earlier quoted context omitted.

That's how the LLMs made you think of your work? You're producing commits now? It's like "content creator" vs "writer" or "artist".

I'm not producing commits. LLMs are producing commits. Fix more things, solve more problems, and do it to a higher degree of quality in less time using LLMs. What's to complain about?

Basically that using "commits" implies a certain degree of psychological detachment from your work. Did you ever use "commits" before LLMs came out?

An actual psychologist could explain it much better than me, but i notice these things.

Re: AI Agents and the Refactoring That Never Happens

#69

Post by teaearlgraycold » Thu, Sep 03, 2026, 11:20 AM UTC

nottorp wrote: post #68

teaearlgraycold wrote: post #67

Earlier quoted context omitted.

I'm not producing commits. LLMs are producing commits. Fix more things, solve more problems, and do it to a higher degree of quality in less time using LLMs. What's to complain about?

Basically that using "commits" implies a certain degree of psychological detachment from your work. Did you ever use "commits" before LLMs came out? An actual psychologist could explain it much better than me, but i notice these things.

Fair enough. I didn’t do most of the work.

Re: AI Agents and the Refactoring That Never Happens

#70

Post by simonw » Thu, Sep 03, 2026, 4:09 PM UTC

nottorp wrote: post #65

teaearlgraycold wrote: post #49

Earlier quoted context omitted.

Not sure what you’re getting at

That's how the LLMs made you think of your work? You're producing commits now? It's like "content creator" vs "writer" or "artist".

I've long thought that commits are the principle unit of work for a software developer. We don't ofter write software from scratch, we modify existing software - and a well crafted commit is a great way to capture that effort.