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

141–150 of 267 posts

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

#141

Post by betenoire »

cortesoft wrote: post #99
lelanthran wrote: post #90

Earlier quoted context omitted.

If I understand your argument, you're saying that models can be deterministic, right? Care to point to any that are set up to be deterministic? Did you ever stop to think about why no one can get any use out of a model with temp set to zero?

No, LLMs ARE deterministic, just like all computer programs are. I get why that is in practice different then the manner in which compilers are deterministic, but my point is the difference isnt because of determinism.

I think you are misunderstanding the term "deterministic". Running on deterministic hardware does not mean an algorithm is deterministic.

Create a program that reads from /dev/random (not urandom). It's not determistic.

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

#142

Post by hathawsh »

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 me to write software for work anymore. I'm a teacher, architect, and infrastructure maintainer now. I hand over most development to my experienced team of Claude sessions. I review everything, but so does Claude (because Claude writes thorough tests also.) It has no problem handling a large project these days.

I don't mean for this post to be an ad for Claude. (Who knows what Anthropic will do to Claude tomorrow?) I intend for this post to be a question: what am I doing that makes Claude profoundly effective?

Also, I'm never running out of tokens anymore. I really only use the Opus model and I find it very efficient with tokens. Just last week I landed over 150 non-trivial commits, all with Claude's help, and used only 1/3 of the tokens allotted for the week. The most commits I could do before Claude was 25-30 per week.

(Gosh, it's hard to write that without coming across as an ad for Anthropic. Sorry.)

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

#143

Post by devilsdata »

onlyrealcuzzo wrote: post #12
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…

> 2. I've learned nothing. So the cognitive load of doing it myself, even assembling a simple docker command, is just too high. Thus, I repeatedly fallback to the "crutch" of using AI. I'm not trying to be offense, so with all due respect... this sounds like a "you" problem. (And I've been there, too) You can ask the LLMs: how do I run this, how do I know this is working, etc etc. Sure... if you really know nothing o…

Good advice. Personally I'm waiting until it is worthwhile to run these models locally, then I'm going to pin a version and just use that.

I'm only 5 years into this career, and I'm going to work manually and absorb as much knowledge as possible while I'm still able to do it. Yes, that means manually doing shit-kicker work. If AI does get so good that I need to use it, as you say, then I'll be running it locally on a version I can master and build tooling for.

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

#144

Post by tabwidth »

soiltype wrote: post #45
ok_dad wrote: post #10

Earlier quoted context omitted.

Why are you letting the LLM drive? Don't turn on auto-approve, approve every command the agent runs. Don't let it make design or architecture decisions, you choose how it is built and you TELL that clanker what's what! No joke, if you treat the AI like a tool then you'll get more mileage out of it. You won't get 10x gains, but you will still understand the code.

Personally I've found "carefully review every move it makes" to be an extremely unpleasant and difficult workflow. The effort needed to parse every action is immense, but there's a complete absence of creative engagement - no chance of flow state. Just the worst kind of work which I've been unable to sustain, unfortunately. At this point I mostly still do work by hand.

Reviewing isn't hard when the diff is what you asked for. It's when you asked for a one-line fix and get back 40 changed lines across four files. At that point you're not even reviewing your change anymore, you're auditing theirs.

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

#145

Post by swader999 »

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 feel the same way. Doesn't make sense economically or even in good faith for me to use company paid time writing code for line of business apps at anymore and I'm 28 years into this kind of work.

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

#146

Post by Powdering7082 »

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…

Is your claude.md, skills or other settings that you have honed public?

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

#147

Post by jdkoeck »

jstanley wrote: post #4

Conversely, I often find coding agents privileging the existing code when they could do a much better job if they changed it to suit the new requirement. I guess it comes down to how ossified you want your existing code to be. If it's a big production application that's been running for decades then you probably want the minimum possible change. If you're just experimenting with stuff and the project didn't exist at…

Tell me you’re using Codex without telling me you’re using Codex :)

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

#148

Post by collimarco »

Over-editing and over-adding... I can find solutions that are just a few lines of code in a single file where AI would change 10 files and add 100s of lines of code. Writing less code is more important than ever. Too much code means more technical debt, a maintainability nightmare and more places where bugs can hide.

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

#149

Post by hathawsh »

Powdering7082 wrote: post #146
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…

Is your claude.md, skills or other settings that you have honed public?

Sorry, no, and they're highly project specific anyway. I just started with the "/init" skill a few weeks ago and gradually improved it from there.

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

#150

Post by p1necone »

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…

Which subscription tier are you using?
Post reply on HN