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

Using AI to write better code more slowly

nolanlawson.com

Post reply on HN
Print view View original

261–270 of 511 posts

Re: Using AI to write better code more slowly

#261

Post by pj_mukh »

aomix wrote: post #59
bottlepalm wrote: post #4

I've hit this point with AI where it's not a simple process, but a long drawn out back and forth. I'll use AI to design the implementation of a medium sized, cross cutting feature. Review all the details, maybe iterate on just that. Then implement with Claude 4.7 Max - which runs slower, but does a better job. Then review the implementation, then have Codex GPT 5.5 xhigh fast review it - which almost always finds cor…

Talking the problem to death with the AI before implementation is a nice zone for me. I feel productive, get good results out of the AI, and still largely understand the code. That’s the part of the AI revolution that I feel has made me a better engineer because I argue about design and architecture all day with a robot.

The professionalization of rubber ducking. I like it.

Re: Using AI to write better code more slowly

#262

Post by youre-wrong3 »

wavemode wrote: post #245
youre-wrong3 wrote: post #211

Earlier quoted context omitted.

[flagged]

What an arrogant comment. You have no idea what kind of software the parent commenter is working on. If you think all software can be handled by AI then I'm afraid you're the one who doesn't know what they're doing.

[flagged]

Re: Using AI to write better code more slowly

#263

Post by williamdclt »

a_bonobo wrote: post #223
throwaway7783 wrote: post #141

Earlier quoted context omitted.

I follow the same process. I have a design in mind for the problem at hand, but I don't reveal it to Codex. I go back and forth a bit to see if its proposals are better than mine. I go back and forth on tradeoffs of various approaches. And then I ask it to compare its proposals with mine. I "win" most of the time but there are many times where it shows a me a better, or simpler approach, or makes me rethink the solut…

I really like this pattern and use it often, this 'not showing my cards'. The second I hint towards the LLM what I prefer it will become sycophantic and invent nonsense why my preferred solution is better. I'm sure there's an interesting study on how users 'leak' their preference unintentionally to the LLM; perhaps when users list their options, they often put their prefered option first; but not showing the cards on…

Same. Alternatively (or in addition), I sometimes present my preferred idea as being a "bad/naive/stupid option" (or a suggestion from someone who can't be trusted) to see how it stands up to sycophancy to it being bad. As expected the LLM will usually say "yeah it's bad!" and give plausible-sounding reasons for it, but if these reasons are nonsensical it's a good sign that I'm not missing anything

Re: Using AI to write better code more slowly

#264

Post by rf_physics »

qsera wrote: post #65
aomix wrote: post #59

Earlier quoted context omitted.

Talking the problem to death with the AI before implementation is a nice zone for me. I feel productive, get good results out of the AI, and still largely understand the code. That’s the part of the AI revolution that I feel has made me a better engineer because I argue about design and architecture all day with a robot.

>I argue about design and architecture all day with a robot. You will outgrow it at some point.

I feel like there's an overly negative vibe to this response when it just seems like rubber duck debugging - I would assume the user isn't trying to argue like how you might have to argue specs, but is merely trying to clarify their own ideas and learn possible alternatives.

Re: Using AI to write better code more slowly

#265

Post by 59nadir »

scosman wrote: post #19
bottlepalm wrote: post #4

I've hit this point with AI where it's not a simple process, but a long drawn out back and forth. I'll use AI to design the implementation of a medium sized, cross cutting feature. Review all the details, maybe iterate on just that. Then implement with Claude 4.7 Max - which runs slower, but does a better job. Then review the implementation, then have Codex GPT 5.5 xhigh fast review it - which almost always finds cor…

yes exactly. Too many people ask AI to one-shot complex tasks, and wonder it behaves like a junior asked to rush something. I have my own skill: 5 rounds of research/planning/test-planning. Interactive with me in loop for all important decisions. Starts with high level shape, then details. Planning can take 2-3 days of my time, then the implementation agent can take many hours (Opus 4.7). It splits the implementation…

My personal experience with trying to front-load tons of planning and speccing out with LLMs is that at best it's a small improvement on code quality but with considerably more time spent.

As a result I've abandoned the idea of having LLMs generate code except for very small, localized and tightly scoped things. They really can't produce much more than a function or a small module without shitting the bed (last time I vibecoded was with Opus 4.6, Composer 2 and GPT-5.4). I use it almost entirely as another signal in analysis, which naturally makes it fit in better because all the other signals (reading the code, stepping through the code, writing the code myself) are already there so when the LLM points things out the information it actually renders can be taken in much more easily (and seen through more easily when it's false or irrelevant).

I think it's neat that people find fun ways to develop, but I think dressing up vibecoding in a fancy dress and layering SpecLang, sometimes in multiple steps, on top of it, is an exercise in trying to use the tool more instead of trying to use it in its most useful capacity.

Re: Using AI to write better code more slowly

#266

Post by deviation »

youre-wrong3 wrote: post #211
justinlivi wrote: post #11

I find myself spending on average more time in LLM review/resolution loops than it would take for me to write the code by hand. Partially because once I'm in the flow I write very very quickly and the code pours out sometimes faster than I can write. But also because the LLM code on the first few tries is generally really really bad. What I find interesting though is that spending the time to personally review and di…

[flagged]

I manage a component of an internal compute product which serves ~a billion idempotent use-cases per quarter and I can confidently tell you that you're incorrect.

What I haven't been able to teach AI is the full distributed nature of the system, how we progressively roll out each service (about ~30 unique ones) when we push updates -- and how to read, write, and review my code while keeping all of this in-context (because believe me, if it's not in-context, it is useless to me). Don't get me started on all the containers, K8s configs, endpoint naming conventions...

My entire stack covers bare metal, virtualisation infrastructure, storage infrastructure... I could go on. At a certain scale, it doesn't matter how fast you write something, but if what you're writing is bulletproof.

Re: Using AI to write better code more slowly

#267

Post by avadodin »

a_bonobo wrote: post #223
throwaway7783 wrote: post #141

Earlier quoted context omitted.

I follow the same process. I have a design in mind for the problem at hand, but I don't reveal it to Codex. I go back and forth a bit to see if its proposals are better than mine. I go back and forth on tradeoffs of various approaches. And then I ask it to compare its proposals with mine. I "win" most of the time but there are many times where it shows a me a better, or simpler approach, or makes me rethink the solut…

I really like this pattern and use it often, this 'not showing my cards'. The second I hint towards the LLM what I prefer it will become sycophantic and invent nonsense why my preferred solution is better. I'm sure there's an interesting study on how users 'leak' their preference unintentionally to the LLM; perhaps when users list their options, they often put their prefered option first; but not showing the cards on…

It's not limited to arguing with LLMs but if you want a honest opinion you should remember to push back even when it agrees with your hidden preference at first. Sometimes it is only being contrarian or supporting the underdog. Steelman the opposition.

Re: Using AI to write better code more slowly

#268

Post by jiggawatts »

bottlepalm wrote: post #4

I've hit this point with AI where it's not a simple process, but a long drawn out back and forth. I'll use AI to design the implementation of a medium sized, cross cutting feature. Review all the details, maybe iterate on just that. Then implement with Claude 4.7 Max - which runs slower, but does a better job. Then review the implementation, then have Codex GPT 5.5 xhigh fast review it - which almost always finds cor…

The funny thing is that you've just described an idealised development process as would be used by effective, skilled humans in a heterogenous team where everyone has a speciality.

If only things were so! If only code was discussed, reviewed, iterated on! If only the "manager" actually read the code, provided actionable feedback, and disseminated PRs to multiple people with diverse skill sets.

(If you can't tell, I'm a jaded consultant desperately trying to make the horse drink the water.)

Re: Using AI to write better code more slowly

#270

Post by youre-wrong3 »

deviation wrote: post #266
youre-wrong3 wrote: post #211

Earlier quoted context omitted.

[flagged]

I manage a component of an internal compute product which serves ~a billion idempotent use-cases per quarter and I can confidently tell you that you're incorrect. What I haven't been able to teach AI is the full distributed nature of the system, how we progressively roll out each service (about ~30 unique ones) when we push updates -- and how to read, write, and review my code while keeping all of this in-context (be…

You literally just proved my point.
Post reply on HN