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

How I write software with LLMs

stavros.io

Post reply on HN
Print view View original

351–360 of 544 posts

Re: How I write software with LLMs

#351

Post by LogicFailsMe »

bhaak wrote: post #317
LogicFailsMe wrote: post #302

Earlier quoted context omitted.

Sounds like influencer nonsense to me. Touch grass. If the people are fed and housed, there's no collapse. And if the billionaire class lets them starve, they will finally go through some things just like the aristocracy in France once did. And I think even Peter Thiel is smarter than that. You can feed yourself for OTOH if what you're really talking about is the long-term collapse in our ludicrous carbon footprint w…

Peter Thiel might be smarter than that but I’m not sure about the other ones. Look how Musk treated the Twitter devs or Bezos any of his workers or Trump anybody.

They're all quite intelligent. And they're world class experts in saving their own bacon. Doesn't mean they have any ethics though nor any emotional intelligence after decades of being surrounded by toadies and bootlickers.

Re: How I write software with LLMs

#352

Post by datsci_est_2015 »

raw_anon_1111 wrote: post #341
datsci_est_2015 wrote: post #330

Earlier quoted context omitted.

I know where they fucked up and cost me thousands of dollars due to cutting corners during build-out and poor architectural decisions during planning. These kinds of things become very obvious during destructive inspection, which is probably why there are so many limitations on warranties; I digress. He’s mildly controversial, but watch some @cyfyhomeinspections on YouTube to get a good idea of what you can infer of…

So you’re saying that whether it’s humans or AI - when you delegate something to others you have no idea whether it’s producing quality without you checking yourself…

> you have no idea whether it’s producing quality without you checking yourself

No, I can have some idea. For example, “brand perception”, which can be negatively impacted pretty heavily if things go south too often. See: GitHub, most recently.

I mean, there are already companies that have a negative reputation regarding software quality due to significant outsourcing (consultancies), or bloated management (IBM), or whatever tf Oracle does. We don’t have to pretend there’s a universe where software quality matters, we already live in one. AI will just be one more way to tank your company’s reputation with regards to quality, even if you can maintain profitability otherwise through business development schemes.

Re: How I write software with LLMs

#353

Post by stavros »

mbesto wrote: post #285
danbruc wrote: post #139

I randomly clicked and scrolled through the source code of Stavrobot - The largest thing I’ve built lately is an alternative to OpenClaw that focuses on security. [1] and that is not great code. I have not used any AI to write code yet but considered trying it out - is this the kind of code I should expect? Or maybe the other way around, has someone an example of some non-trivial code - in size and complexity - writt…

> and that is not great code When you say "is not great code" can you elaborate? Does the code work or not?

It works really well, multiple people have been using it for a month or so (including me) and it's flawless. I think "not great" means "not very readable by humans", but it wasn't really meant to be readable.

I don't know if there are underlying bugs, but I haven't hit any, and the architecture (which I do know about) is sane.

Re: How I write software with LLMs

#354

Post by stavros »

FiberBundle wrote: post #245
danbruc wrote: post #139

I randomly clicked and scrolled through the source code of Stavrobot - The largest thing I’ve built lately is an alternative to OpenClaw that focuses on security. [1] and that is not great code. I have not used any AI to write code yet but considered trying it out - is this the kind of code I should expect? Or maybe the other way around, has someone an example of some non-trivial code - in size and complexity - writt…

Pine Town [1], the "whimsical infinite multiplayer canvas of a meadow", also looks like pure slop. [1] https://pine.town/

What were you hoping to achieve with this comment?

Re: How I write software with LLMs

#355

Post by raw_anon_1111 »

throwaw12 wrote: post #345
raw_anon_1111 wrote: post #291

Earlier quoted context omitted.

In the past ten years as a team lead/architect/person who was responsible for outsourced implementations (ie Salesforce/Workday integrations, etc), I’ve been responsible for a lot of code I didn’t write. What sense would it have made for me to review the code of the web front end of the web developer for best practices when I haven’t written a web app since 2002?

as a team lead, if you are not aware of what's happening in the team, what kind of team lead is this? on the other hand, you may have been an engineering manager, who is responsible for the team, but a lot of times they do not participate in on-call rotations (only as last escalation)

As a team lead, I know the architecture, the functional and non functional requirements, I know the website is suppose to do $x but I definitely didn’t guide how since I haven’t done web development in a quarter century, I know the best practices for architecture and data engineering (to a point).

That doesn’t mean I did a code review for all of the developers. I will ask them how they solved for a problem that I know can be tricky or did they take into account for something.

Re: How I write software with LLMs

#356

Post by never_inline »

danbruc wrote: post #155
never_inline wrote: post #145

Earlier quoted context omitted.

I would suggest not delegating the LLD (class / interface level design) to the LLM. The clankeren are super bad at it. They treat everything as a disposable script. Also document some best practices in AGENT.md or whatever it's called in your app. Eg * All imports must be added on top of the file, NEVER inside the function. * Do not swallow exceptions unless the scenario calls for fault tolerance. * All functions nee…

What actually stood out to me is how bad the functions are, they have no structure. Everything just bunched together, one line after the other, whatever it is, and almost no function calls to provide any structure. And also a ton of logging and error handling mixed in everywhere completely obscuring the actual functionality. EDIT: My bad, the code eventually calls into dedicated functions from database.ts, so those 2…

Which reinforces my point that LLMs are really bad at class and module level design.

Re: How I write software with LLMs

#357

Post by LogicFailsMe »

sarchertech wrote: post #334
LogicFailsMe wrote: post #302

Earlier quoted context omitted.

Sounds like influencer nonsense to me. Touch grass. If the people are fed and housed, there's no collapse. And if the billionaire class lets them starve, they will finally go through some things just like the aristocracy in France once did. And I think even Peter Thiel is smarter than that. You can feed yourself for OTOH if what you're really talking about is the long-term collapse in our ludicrous carbon footprint w…

>Sounds like influencer nonsense to me. Touch grass. I don't even know what this means. The worst unemployment during the Weimar Republic was 25-30%. Unemployment in the Great Depression peaked at 25%. So yeah if we get to 45% unemployment and those are the highest paying jobs on average then yeah it's gonna be bad. Then you add in second order effects where none of those people have the money to pay the other 55% wh…

And the dark ages lasted a millennium. Sounds like quite an improvement on that. And if America didn't want a society hellbent on living the worst possible timeline, why did it re-elect President Voldemaga and give him the football? And then, even when he breaks nearly every political promise, his support remains better than his predecessor? Anyway, I think the richest ~1135 Americans won't let you starve, but they'll be happy to watch you die young of things that had stopped killing people for quite some time whilst they skim all the cream. And that seems to be what the plurality wants or they'd vote differently.

The good news is that America is ~5% of the world. And the more we keep punching ourselves in the face, the better the chance someone else pulls ahead. But still, we have nukes, so we're still the town bully for the immediate future.

Re: How I write software with LLMs

#358

Post by dml2135 »

pathikrit wrote: post #288

10-15 years ago HN was the place where everyone showed off their new shiny toys and people would jump over themselves to try some new framework or db or tool. Now, so much negative sentiment about AI coding. I bet if LLMs came 15 years ago, HN would be brimming with excitement. What happened?

Oligarchy.

Re: How I write software with LLMs

#359

Post by raw_anon_1111 »

datsci_est_2015 wrote: post #352
raw_anon_1111 wrote: post #341

Earlier quoted context omitted.

So you’re saying that whether it’s humans or AI - when you delegate something to others you have no idea whether it’s producing quality without you checking yourself…

> you have no idea whether it’s producing quality without you checking yourself No, I can have some idea. For example, “brand perception”, which can be negatively impacted pretty heavily if things go south too often. See: GitHub, most recently. I mean, there are already companies that have a negative reputation regarding software quality due to significant outsourcing (consultancies), or bloated management (IBM), or…

So as long as it is meeting the requirements of “it stays up consistently and doesn’t lose my code” you really don’t care how it was coded…

The same as I’ve been arguing about using an agent to do the grunt work of coding.

If GitHub’s login is slow, it isn’t because someone or something didn’t write SOLID code.

Re: How I write software with LLMs

#360

Post by raw_anon_1111 »

zackify wrote: post #239
miguelgrinberg wrote: post #151

> One thing I’ve noticed is that different people get wildly different results with LLMs, so I suspect there’s some element of how you’re talking to them that affects the results. It's always easier to blame the prompt and convince yourself that you have some sort of talent in how you talk to LLMs that other's don't. In my experience the differences are mostly in how the code produced by the LLM is reviewed. Develope…

This definitely is the case. I was talking to someone complaining about how llms don't work good. They said it couldn't fix an issue it made. I asked if they gave it any way to validate what it did. They did not, some people really are saying "fix this" instead of saying "x fn is doing y when someone makes a request to it. Please attempt to fix x and validate it by accessing the endpoint after and writing tests" Its…

I made that mistake when I first started using Claude Code/Codex. Now I give it access to my isolated DEV AWS account with appropriately scoped permissions on the IAM level with temporary credentials and tell it how to validate the code and have in my markdown file to always use $x to test any changes to $y.

It’s gotten a lot better.

Post reply on HN