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

When I reject AI code even if it works

vinibrasil.com

Post reply on HN
Print view View original

121–130 of 184 posts

Re: When I reject AI code even if it works

#121

Post by Agentlien »

mkozlows wrote: post #45
ecshafer wrote: post #13

If we rephrased this to "When I reject my coworkers code even if it works" and give the same reasons there would be zero dissent. There is this weird idea that seems to come up with AI that any solution must be good and adequate. Software Engineering is all about rejecting code that works for the right code that works.

Yeah, but I think there's a difference here: If your coworker puts up code that you don't understand quickly, in most environments people give it an approval, as withholding approval is meant to indicate that there's a problem with the code. It's very rare that you'd actually force them to wait to merge until they've explained the code to your satisfaction. (There are workplaces where that's the norm, I know -- it te…

On the teams where I've worked which had a proper code review policy not understanding has been explicitly stated as a reason to pause and ask for clarification. You cannot give a pass for code you don't understand.

Re: When I reject AI code even if it works

#122

Post by neonstatic »

The more I look into it, the more I am convinced, that I don't want any AI generated code in my project. I find the LLM useful to talk things through. It can offer some interesting takes during the design and acts as a decent rubber duck companion when debugging. It is also very helpful when I need some help with syntax and/or feature discovery.

> I reject AI code when I can’t explain the approach in my own words.

I think that's the key problem. LLMs turn code into big, black boxes. Sure, theoretically nothing stops me from reading all that code. I don't, however, because it's wasted effort. The time it takes me to really understand the code is IMO better spent just writing it myself. Once written, I have a very good understanding. Read ten times, not so much.

It reminds me of pen and paper. Journaling the old way remains the best way to learn something, but writing on a computer is much more convenient.

Re: When I reject AI code even if it works

#123

Post by endofreach »

ffsm8 wrote: post #112
abhgh wrote: post #25

Earlier quoted context omitted.

These "You're right to push back" scenarios are scary for me. I mostly code ML implementations, and some of the errors Claude Code (CC - have only used Opus 4.7) makes are very sneaky, and if you don't have sufficient experience in the area (I see this with people entering ML and writing their implementations with CC), you wouldn't know when to question CC and will let errors or future pitfalls silently slip into you…

What's mind-blowing to me is that people see the "you're right to push back" as anything besides hallucination / self affirmation Dude, the fucking model is great for sure, but there is nothing behind the illusion. It doesn't know if something is right or wrong - simpler or harder to reason about etc It's just generating text, in a coherent manner while following rhetoric processes as a solid attempt at logical think…

We'll see.

Re: When I reject AI code even if it works

#124

Post by Planktonne »

lemagedurage wrote: post #116
Planktonne wrote: post #111

Earlier quoted context omitted.

It's been years at this point though; everyone knows where "use AI as a code writing aid" ends up.

I think the differentiator is whether someone cares about what they build or not. Someone who doesn't care wouldn't produce masterpieces without AI, and using AI isn't going to prevent someone who does care from building something nice.

But everyone claims they care; everyone using AI is telling you that they're not like the slop merchants, that they're really building masterpieces/the next unicorn. Just like everyone using AI to write says they're just using it as a fancier spellcheck.

It doesn't seem like AI users are very good at telling how much or how well they're using it.

Re: When I reject AI code even if it works

#125

Post by SunboX »

PacificSpecific wrote: post #100
SunboX wrote: post #99

I unterstand the reasons, but I don't think so. I have experience in software development over 20 years now and still developing software daily. Nowadays it's nearly 100℅ AI written. It looks good and works. Sure, you have to guide the AI. But this can be done with custom skills, angent files, code quality guards test cases and so on. Maybe the code looks at the end not as I would have written it, maybe something is…

That's cool. Could you share some concrete examples of your successes?

One I currently working on (privately) is ecadforge.app

The last ones, I worked on in Industry are retail7 apps, Migros Self scanning client, EDEKA, LIDL and so on customer facing apps.

My private interest is more in electronics.

Re: When I reject AI code even if it works

#126

Post by sltr »

It's kind of like the saying "the right note played at the wrong time is wrong." An implementation that works today but could break in the future is wrong. I'm not willing to treat an LLM as an oracle that knows the difference. It certainly hasn't earned that trust.

Re: When I reject AI code even if it works

#127

Post by simondotau »

jdw64 wrote: post #40

Coding with AI eventually comes down to two paths, I've realized. One is using AI exclusively for everything. The other is not using it at all. There is almost no middle ground. The reason is that as the complexity and depth of the problem increase, the code AI generates increasingly follows enterprise level patterns. The deeper the meaning of what I input, the more AI tends to produce code that goes beyond my own ar…

I feel like my current approach is a decent middle ground.

In the past, I wrote code by first writing English pseudo-code as a series of self-documenting comments. These would be declarative assertions of what the code will do. (For example, "Method returns true if array values are within 0.5% of spherical.") I then wrote the real code next to each comment.

My current workflow is mostly the same as before, but as soon as I think there's nothing creative left to do, I allow AI to take a pass at it, insisting it include verbose comments. Next I read everything; its comments are often redundant but allow me to internalise the logic/intent more quickly. I make any corrections myself. And I strip any pointless AI comments.

In short, I stay in full control of the architecture while tasking AI with the grunt work, the implementation details, and the superficial correctness.

Re: When I reject AI code even if it works

#128

Post by SunboX »

tom2026hn wrote: post #120
SunboX wrote: post #99

I unterstand the reasons, but I don't think so. I have experience in software development over 20 years now and still developing software daily. Nowadays it's nearly 100℅ AI written. It looks good and works. Sure, you have to guide the AI. But this can be done with custom skills, angent files, code quality guards test cases and so on. Maybe the code looks at the end not as I would have written it, maybe something is…

Do you still need to review the code? LLMs generate code too quickly for humans to keep up.

Yes, but I can not review all anymore. It's too much code. But I at least "scroll" over all the code and check if I can spot something obvious. But you can not hold up anymore. I guess, you have to trust and react fast if something goes wrong. It has become more stressful.

Re: When I reject AI code even if it works

#129

Post by SunboX »

PacificSpecific wrote: post #100
SunboX wrote: post #99

I unterstand the reasons, but I don't think so. I have experience in software development over 20 years now and still developing software daily. Nowadays it's nearly 100℅ AI written. It looks good and works. Sure, you have to guide the AI. But this can be done with custom skills, angent files, code quality guards test cases and so on. Maybe the code looks at the end not as I would have written it, maybe something is…

That's cool. Could you share some concrete examples of your successes?

Otherwise I quickly did some smaller projects lately, mainly AI driven. Just take a look at my list here: https://github.com/SunboX?tab=repositories

Re: When I reject AI code even if it works

#130

Post by Obscurity4340 »

ffsm8 wrote: post #112
abhgh wrote: post #25

Earlier quoted context omitted.

These "You're right to push back" scenarios are scary for me. I mostly code ML implementations, and some of the errors Claude Code (CC - have only used Opus 4.7) makes are very sneaky, and if you don't have sufficient experience in the area (I see this with people entering ML and writing their implementations with CC), you wouldn't know when to question CC and will let errors or future pitfalls silently slip into you…

What's mind-blowing to me is that people see the "you're right to push back" as anything besides hallucination / self affirmation Dude, the fucking model is great for sure, but there is nothing behind the illusion. It doesn't know if something is right or wrong - simpler or harder to reason about etc It's just generating text, in a coherent manner while following rhetoric processes as a solid attempt at logical think…

How does it correct itself then? I often will push back without giving it the way out and it often does find it
Post reply on HN