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

251–260 of 267 posts

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

#251

Post by Shorel »

anonu wrote: post #5

Here, the author means the agent over-edits code. But agents also do "too much": as in they touch multiple files, run tests, do deployments, run smoke tests, etc... And all of this gets abstracted away. On one hand, its incredible. But on the other hand I have deep anxiety over this: 1. I have no real understanding of what is actually happening under the hood. The ease of just accepting a prompt to run some script th…

> So the cognitive load of doing it myself, even assembling a simple docker command, is just too high.

The cognitive load is not too high. You're just addicted. I would even say, lazy.

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

#253

Post by htfu »

kaoD wrote: post #244
maxbond wrote: post #156

Earlier quoted context omitted.

When I see people talking about Claude Code becoming "unusable" for them recently, I believe them, but I don't understand. It's a deeply flawed and buggy piece of software but it's very effective. One of the strangest things about AI to me is that everyone seems to have a radically different experience.

> everyone seems to have a radically different experience What people have is radically different expectations. I noticed engineers will review Claude's output and go "holy crap that's junior-level code" . Coders will just commit because looking at the code is a waste of time. Move fast, break things, disrupt, drown yourself into tech debt: the investors won't care anyways. And no, telling the agent to "be less shit"…

You have to tell it both what and how. That way it's decidedly less shit. Still needs tons of passes just keeping things somewhat coherent, but it mostly works.

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

#254

Post by lw1981 »

I’ve run into this in debugging too. I had one case where the model fixed a bug in concurrent execution code by basically making it sequential. So yes, the bug disappeared, but only because it removed the concurrency property instead of actually solving the underlying issue.

That kind of thing has made me much more cautious about judging these tools purely by whether the immediate error went away.

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

#255

Post by jffhn »

esafak wrote: post #81
ramesh31 wrote: post #11

Earlier quoted context omitted.

>The idea being that if you're working in an area, you should refactor and tidy it up and clean up "tech debt" while there. This is horrible practice, and very typical junior behavior that needs to be corrected against. Unless you wrote it, Chesterton's Fence applies; you need to think deeply for a long time about why that code exists as it does, and that's not part of your current task. Nothing worse than dealing wi…

Just do it in a follow up PR to keep them atomic. But do clean up; it's so easy now.

Before, not after: when the code makes it hard to implement a new feature (the definition of technical debt: code that is properly designed but only for previous features), first refactor the code to make the feature easy to implement, then implement the feature.

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

#256

Post by Abby_101 »

The over-editing cost is asymmetric when you're solo. If an agent rewrites 50 lines when you asked it to touch 5, there's no second reviewer behind you. You're the writer and the reviewer, and reviewer (you) is usually the one whose attention is already depleted. What helped me most wasn't prompting tricks but committing after every turn so I can revert cheaply and re-prompt with tighter constraints. Cheaper than auditing a 400-line diff at 11pm.

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

#257

Post by Isolated_Routes »

mleo wrote: post #161
Isolated_Routes wrote: post #56

I think building something really well with AI takes a lot of work. You can certainly ask it to do things and it will comply, and produce something pretty good. But you don't know what you don't know, especially when it speaks to you authoritatively. So checking its work from many different angles and making sure it's precise can be a challenge. Will be interesting to see how all of this iterates over time.

If I don’t know what I don’t know, how am I going to build something any better than a coding agent? An approach on a couple of projects has been to prototype with the agent, learn, write a design and then start over. I then know the areas to look into more detail.

That's really the catch, and I think we're just figuring out how to approach this. I think your iteration approach is correct. I do a lot of asking AI to tell me about blind spots, to double check it's work in specific ways. I've asked it to let me know what it might have hallucinated, where it cut corners, and a bunch of other things along these lines. It will be interesting to see how things evolve in this area, and if AI gets good to the point that we have to do this less.

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

#258

Post by kowbell »

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…

> In terms of limits, I usually find myself hitting the rate limit after two or three requests.

I'd absolutely love to see exactly what you're doing (...well, maybe in a world where I had unlimited time or could clone myself...) because as tight as the usage limits are I absolutely cannot fathom hitting them THAT early.

What are the requests like, and have you noticed what is Claude doing during them? Is it reading an entire massive codebase or files that are thousands of lines long? Or are you loaded up with many MCPs or have an ever-growing CLAUDE.md?

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

#260

Post by kristianp »

graybeardhacker wrote: post #37

I use Claude Code every day and have for as long as it has been available. I use git add -p to ensure I'm only adding what is needed. I review all code changes and make sure I understand every change. I prompt Claude to never change only whitespace. I ask it to be sure to make the minimal changes to fix a bug. Too many people are treating the tools as a complete replacement for a developer. When you are typing a text…

`git add -p` sounds like a useful tool to try.
Post reply on HN