Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Over-editing refers to a model modifying code beyond what is necessary

nrehiew.github.io

Post reply on HN
Print view View original

211–220 of 267 posts

Re: Over-editing refers to a model modifying code beyond what is necessary

#211

Post by nicbou »

hathawsh wrote: post #142

I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. When it makes a mistake like over-editing, I explain the mistake, it fixes it, and I ask it to record what it learned in the relevant project-specific skills. It rarely makes that mistake again. When the skill file gets big, I ask Claude to clean and compact it. It does a great job. It doesn't really make sense economically for…

Same. It's surprisingly good as a labour saving device. It produces code that I would accept without reservations from a coworker. I still read every line and make tweaks, but they're the same tweaks I would ask for in a code review.

I don't measure my productivity, but I see it in the sort of tasks I tackle after years of waiting. It's especially good at tedious tasks like turning 100 markdown files into 5 json files and updating the code that reads them, for example.

Re: Over-editing refers to a model modifying code beyond what is necessary

#213

Post by theshrike79 »

Swizec wrote: post #155
hathawsh wrote: post #142

I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. When it makes a mistake like over-editing, I explain the mistake, it fixes it, and I ask it to record what it learned in the relevant project-specific skills. It rarely makes that mistake again. When the skill file gets big, I ask Claude to clean and compact it. It does a great job. It doesn't really make sense economically for…

> I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. I looked at some stats yesterday and was surprised to learn Cursor AI now writes 97% of my code at work. Mostly through cloud agents (watching it work is too distracting for me) My approach is very simple: Just Talk To It People way overthink this stuff. It works pretty good. Sharing .md files and hyperfocusing on various orch…

The trick is to "just use it", BUT every few weeks grab the logs (you do keep them, right?) and have a session with the model to find out if there are any repeated patterns.

If you find any, consider making them into skills or /commands or maybe even add them to AGENTS.md.

Re: Over-editing refers to a model modifying code beyond what is necessary

#214

Post by cassianoleal »

ramesh31 wrote: post #154
cassianoleal wrote: post #25

Earlier quoted context omitted.

That is the flip side of what you're arguing against, and is also very typical junior behaviour that needs to be corrected against. Tech debt needs to be dealt with when it makes sense. Many times it will be right there and then as you're approaching the code to do something else. Other times it should be tackled later with more thought. The latter case is frequently a symptom of the absence of the former. In Extreme…

Indeed there's a distinction that needs to be made here between "not refactoring this code means I'll need to add hacks" and "Oh I'll just clean that up while I'm in here." The former can be necessary, but the latter is something you learn with experience to avoid.

> the latter is something you learn with experience to avoid.

The latter is something you learn to judge the right time to tackle. Sometimes a small improvement that's not required will mean you're not pressed to make the refactor to avoid hacks. The earliest you can tackle problems, the cheaper they are to solve.

Re: Over-editing refers to a model modifying code beyond what is necessary

#215

Post by phito »

Swizec wrote: post #155
hathawsh wrote: post #142

I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. When it makes a mistake like over-editing, I explain the mistake, it fixes it, and I ask it to record what it learned in the relevant project-specific skills. It rarely makes that mistake again. When the skill file gets big, I ask Claude to clean and compact it. It does a great job. It doesn't really make sense economically for…

> I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. I looked at some stats yesterday and was surprised to learn Cursor AI now writes 97% of my code at work. Mostly through cloud agents (watching it work is too distracting for me) My approach is very simple: Just Talk To It People way overthink this stuff. It works pretty good. Sharing .md files and hyperfocusing on various orch…

You're wasting a ton of tokens doing that though. Right now you don't realize it because they're being heavily subsidized, but you will understand the point of have good orchestration and memory files when you will have to pay the real cost of your use.

Re: Over-editing refers to a model modifying code beyond what is necessary

#216

Post by Calavar »

hathawsh wrote: post #142

I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. When it makes a mistake like over-editing, I explain the mistake, it fixes it, and I ask it to record what it learned in the relevant project-specific skills. It rarely makes that mistake again. When the skill file gets big, I ask Claude to clean and compact it. It does a great job. It doesn't really make sense economically for…

It's interesting how variable people's experiences seem to be.

Personally, I tend to get crap quality code out of Claude. Very branchy. Very un-DRY. Consistently fails to understand the conventions of my codebase (e.g. keeps hallucinating that my arena allocator zero initializes memory - it does not). And sometimes after a context compaction it goes haywire and starts creating new regressions everywhere. And while you can prompt to fix these things, it can take an entire afternoon of whack-a-mole prompting to fix the fallout of one bad initial run. I've also tried dumping lessons into a project specific skill file, which sometimes helps, but also sometimes hurts - the skill file can turn into a footgun if it gets out of sync with an evolving codebase.

In terms of limits, I usually find myself hitting the rate limit after two or three requests. On bad days, only one. This has made Claude borderline unusable over the past couple weeks, so I've started hand coding again and using Claude as a code search and debugging tool rather than a code generator.

Re: Over-editing refers to a model modifying code beyond what is necessary

#217

Post by mirekrusin »

phito wrote: post #215
Swizec wrote: post #155

Earlier quoted context omitted.

> I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. I looked at some stats yesterday and was surprised to learn Cursor AI now writes 97% of my code at work. Mostly through cloud agents (watching it work is too distracting for me) My approach is very simple: Just Talk To It People way overthink this stuff. It works pretty good. Sharing .md files and hyperfocusing on various orch…

You're wasting a ton of tokens doing that though. Right now you don't realize it because they're being heavily subsidized, but you will understand the point of have good orchestration and memory files when you will have to pay the real cost of your use.

Cost cannot go up, only down with time (with occasional short term fluctuations). Competition, including open weight models and consumer hardware (ie upcoming M5 Ultra) keeps moving ceiling of what you can charge down.

Re: Over-editing refers to a model modifying code beyond what is necessary

#218

Post by jampekka »

Calavar wrote: post #216
hathawsh wrote: post #142

I'm either in a minority or a silent majority. Claude Code surpasses all my expectations. When it makes a mistake like over-editing, I explain the mistake, it fixes it, and I ask it to record what it learned in the relevant project-specific skills. It rarely makes that mistake again. When the skill file gets big, I ask Claude to clean and compact it. It does a great job. It doesn't really make sense economically for…

It's interesting how variable people's experiences seem to be. Personally, I tend to get crap quality code out of Claude. Very branchy. Very un-DRY. Consistently fails to understand the conventions of my codebase (e.g. keeps hallucinating that my arena allocator zero initializes memory - it does not). And sometimes after a context compaction it goes haywire and starts creating new regressions everywhere. And while yo…

> Very branchy. Very un-DRY.

I've found this can be vastly reduced with AGENTS.md instructions, at least with codex/gpt-5.4.

Re: Over-editing refers to a model modifying code beyond what is necessary

#219

Post by Calavar »

jampekka wrote: post #218
Calavar wrote: post #216

Earlier quoted context omitted.

It's interesting how variable people's experiences seem to be. Personally, I tend to get crap quality code out of Claude. Very branchy. Very un-DRY. Consistently fails to understand the conventions of my codebase (e.g. keeps hallucinating that my arena allocator zero initializes memory - it does not). And sometimes after a context compaction it goes haywire and starts creating new regressions everywhere. And while yo…

> Very branchy. Very un-DRY. I've found this can be vastly reduced with AGENTS.md instructions, at least with codex/gpt-5.4.

What sorts of instructions?

Re: Over-editing refers to a model modifying code beyond what is necessary

#220

Post by jampekka »

Calavar wrote: post #219
jampekka wrote: post #218

Earlier quoted context omitted.

> Very branchy. Very un-DRY. I've found this can be vastly reduced with AGENTS.md instructions, at least with codex/gpt-5.4.

What sorts of instructions?

Usually I just put something like "Prefer DRY code". I like to keep my AGENTS.md DRY too :)
Post reply on HN