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

How to effectively write quality code with AI

heidenstedt.org

Post reply on HN
Print view View original

241–250 of 321 posts

Re: How to effectively write quality code with AI

#241

Post by dw_arthur »

p1esk wrote: post #226
shinycode wrote: post #220

Earlier quoted context omitted.

Do you mean, from your perspective, within 2 years humans won’t be able to bring anything of value to the equation in management and control ?

No, I mean that my job in its current form – as an ML researcher with a phd and 15 years of experience - will be completely automated within two years.

Is the progress of LLMs moving up abstraction layers inevitable as they gather more data from each layer? First, we fed LLMs raw text and code and now they are gathering our interactions with the LLM regarding generated code. It seems like you could then use the interactions to make a LLM that is good at prompting and fixing another LLMs generated code. Then its on to the next abstraction layer.

Re: How to effectively write quality code with AI

#242

Post by whoisthemachine »

raw_anon_1111 wrote: post #160
AdieuToLogic wrote: post #148

Earlier quoted context omitted.

> A lot of how I form my thoughts is driven by writing code, and seeing it on screen, running into its limitations. Two principles I have held for many years which I believe are relevant both to your sentiment and this thread are reproduced below. Hopefully they help. First: When making software, remember that it is a snapshot of your understanding of the problem. It states to all, including your future-self, your ap…

To your first point - so are my many markdown files that I tell Codex/Claude to keep updated while I’m doing my work including telling them to keep them updated with why I told them to do certain things. They have detailed documentation of my initial design goals and decisions that I wrote myself. Actually those same markdown files answer the second question.

It's almost like programming via markdown.

Re: How to effectively write quality code with AI

#243

Post by raw_anon_1111 »

skydhash wrote: post #240
raw_anon_1111 wrote: post #223

Earlier quoted context omitted.

No one who has any knowledge or who has ever used an LLM expects determinism. And there are no computer professionals who haven’t heard about hallucinations. Reviewing whether the code meets requirements through manual and automated tests - and that’s all I cared about when I had a team of 8 under me - is the same regardless. I wasn’t checking whether John used a for loop or while loop in between my customer meetings…

There are so many types of requirements though. Security is one, performance is another. No one has cared about while/for for a long time.

Okay - and the person ultimately leading the team is still responsibility for it whether you are delegating to more junior developers or AI. You’re still reviewing someone else’s code based on your specs

Re: How to effectively write quality code with AI

#244

Post by whoisthemachine »

orwin wrote: post #65
krashidov wrote: post #39

> Use strict linting and formatting rules to ensure code quality and consistency. This will help you and your AI to find issues early. I've always advocated for using a linter and consistent formatting. But now I'm not so sure. What's the point? If nobody is going to bother reading the code anymore I feel like linting does not matter. I think in 10 years a software application will be very obfuscated implementation c…

That's the opposite. I've never read and re-read code more than i do today. The new hires generate 50 more code than they use to, and you _have_ to check it or have compounding production issues (been there, done that). And the errors can now be anywhere, when before you more or less knew what the person writing code is thinking and can understand why some errors are made. LLMs errors could hide _anywhere_, so you ha…

You don't have to. How else are the new hires going to learn the downsides of outputting so much unreadable BS?

Re: How to effectively write quality code with AI

#245

Post by raw_anon_1111 »

whoisthemachine wrote: post #242
raw_anon_1111 wrote: post #160

Earlier quoted context omitted.

To your first point - so are my many markdown files that I tell Codex/Claude to keep updated while I’m doing my work including telling them to keep them updated with why I told them to do certain things. They have detailed documentation of my initial design goals and decisions that I wrote myself. Actually those same markdown files answer the second question.

It's almost like programming via markdown.

Or like every tech lead has had to do when documenting specifications for a team…

Re: How to effectively write quality code with AI

#247

Post by whynotminot »

chrisjj wrote: post #218
whynotminot wrote: post #98

Earlier quoted context omitted.

Anyone who’s been a developer for more than 10 minutes knows that best practices are hard to always follow through on when there’s pressure to ship. But there’s more time to do some of these other things if the actual coding time is trending toward zero. And the importance of it can go up with AI systems because they do actually use the documentation you write as part of their context! Direct visible value can lead p…

> Anyone who’s been a developer for more than 10 minutes knows that best practices are hard to always follow through on when there’s pressure to ship. > But there’s more time to do some of these other things if the actual coding time is trending toward zero. I think you'll find even less time - as "AI" drives the target time to ship toward zero.

I agree that this will be the end result over time, maybe even faster than we expect. And as those speed pressures increase, AI will take over more and more of the development process.

Re: How to effectively write quality code with AI

#248

Post by Forge36 »

emsign wrote: post #35

Sounds like an awful lot of work and nannying just to avoid writing code yourself. Coding used to be fun and enjoyable once...

I'm still writing code. I'm doing it to solve a problem, there's more to writing code than than typing. Recently AI massively simplified "getting started", and all of the tips here are applicable to working well on a team.

My recent experience: I'm porting an app to Mac. It's been in my backlog for ~2 years. With Claude I had a functional prototype in under a day getting the major behavior implemented. I spent the next two weeks refactoring the original app to share as much logic as possible. The first two days was lots of fun. The refactoring was also something I wanted to flush out unit tests, still enjoyable.

The worst part was debugging really bugs introduced to my code from 5 years ago. My functions had naming issues describing the behavior wrong, confusing Claude, that I needed to re-understand to add new features.

Parts of coding are frustrating. Using AI is frustrating for different reasons.

The most frustrating part was rebasing with git to create a sensible history (which I've had to do without AI in the past), reviewing the sheer volume of changes (14k lines) and then deciding "do I want my name on this" which involved cleaning up all the linter warnings I'd self imposed on myself.

Re: How to effectively write quality code with AI

#249

Post by ensemblehq »

OptionOfT wrote: post #2

I wonder at the end of this if it's the still worth the risk? A lot of how I form my thoughts is driven by writing code, and seeing it on screen, running into its limitations. Maybe it's the kind of work I'm doing, or maybe I just suck, but the code to me is a forcing mechanism into ironing out the details, and I don't get that when I'm writing a specification.

This is exactly the issue I’m facing especially when working with AI-generated codebases.

Coding is significantly faster but my understanding of the system takes a lot longer because I’m having to merge my mental model with what was produced.

Re: How to effectively write quality code with AI

#250

Post by meetingthrower »

jochem9 wrote: post #184
coldtea wrote: post #168

Earlier quoted context omitted.

The previous second order effect is more likely. For the one orchestrating 8 bots, 7 others are not needed anymore.

So far in my career I have always had more requests coming in than implementations going out. If I can go 3 or 10 times faster, than I will still have plenty of work. Especially for the slew of ideas that are never even considered to put towards a dev, because it's already considered to be too low value to have it even be considered to be build. Or the ideas that are so far fetched they were never considered feasible…

This 100%. We want MOAR!!!
Post reply on HN