How I write software with LLMs • Hacker News Board

Re: How I write software with LLMs

#321

Post by datsci_est_2015 » Mon, Mar 16, 2026, 2:34 PM UTC

AIorNot wrote: post #295

datsci_est_2015 wrote: post #266

Earlier quoted context omitted.

> you are overestimating the skill of code review. “You are overestimating the skill of [reading, comprehending, and critically assessing code of a non-guaranteed quality]” is an absurd statement if you properly expand out what “code review” means. I don’t care if you code review the CSS file for the Bojangles online menu web page, but you better be code reviewing the firmware for my dad’s pacemaker. This whole back…

By far most of the code LLMs write is for crappy crud apps and webapps not pacemakers and rockets We can capture enough reliability on what LLMs produce there by guided integration tests and UX tests along with code review and using other LLMs to review along with other strategies to prvent semantic and code drift Do you know how much crap wordpress ,drupal and Joomla sites I have seen? Just that work can be automate…

> that’s just moving the goalposts on what AI can do- it will get there eventually

This is the nutshell of your argument. I’m not convinced. Technologies often hit a ceiling of utility.

Imagine a “progress curve” for every technology, x-axis time and y-axis utility. Not every progress curve is limitlessly exponential, or even linear - in fact, very few are. I would venture to guess that most technological progress actually mimics population growth curves, where a ceiling is hit based on fundamental restrictions like resource availability, and then either stabilizes or crashes.

I don’t think LLMs are the AI endgame. They definitely have utility, but I think your argument boils down to a bold prediction of limitless progress of a specific technology (LLMs), even though that’s quite rare historically.

Re: How I write software with LLMs

#322

Post by benterris » Mon, Mar 16, 2026, 2:35 PM UTC

One thing I don't get with this workflow, and all the ones we see in similar articles: do the authors run their agents in YOLO mode (full unchecked permission on their machine)? It seems their agents have full edit rights (scoped to a directory, which seems reasonable), but can also run tests autonomously (which means they can run any code), which equates to full read/write access on the machine? I mean, there are ways to sandbox agents in dedicated containers, but it requires quite a bit of setup, and none of these articles mention it, so I guess they are YOLOing it?

Re: How I write software with LLMs

#323

Post by jjice » Mon, Mar 16, 2026, 2:36 PM UTC

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…

I think that's absolutely part of it. Code reviewing has become an even more valuable skill than ever, and I think the industry as a whole still is treating it as low value, despite it always being one of the most important parts of the process.

I think another part (among many others) is not the skill of the individual prompting, but on the quality of the code and documentation (human and agent specific) in the code base. I've seen people run willy-nilly with LLMs that are just spitting out nonsense because there are no examples for how the code should look, not documentation on how it should structure the code, and no human who knows what the code should work reviewing it. A deadly combo to produce bad, unmaintainable code.

If you sort those out though (and review your own damn LLM code), I think that's when LLMs become a powerful programming tool.

I really liked Simon Willison's way of putting it: "Your job is to deliver code you have proven to work".

https://simonwillison.net/2025/Dec/18/code-proven-to-work/

Re: How I write software with LLMs

#324

Post by jplusequalt » Mon, Mar 16, 2026, 2:37 PM UTC

LogicFailsMe wrote: post #302

sarchertech wrote: post #280

Earlier quoted context omitted.

That depends on how fast that change happens. If 45% of jobs evaporate in a a 5 year period, a complete societal collapse is the likely outcome.

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…

>You can feed yourself for You are the epitome of the tech bro.

Re: How I write software with LLMs

#325

Post by raw_anon_1111 » Mon, Mar 16, 2026, 2:37 PM UTC

jplusequalt wrote: post #320

LogicFailsMe wrote: post #276

Earlier quoted context omitted.

I don't see a world where a motivated soul can build a business from a laptop and a token service as a problem. I see it as opportunity. I feel similarly about Hollywood and the creation of media. We're not there in either case yet, but we will be. That's pretty clear. and when I look at the feudal society that is the entertainment industry here, I don't understand why so many of the serfs are trying to perpetuate it…

>If you can build things, AI coding agents will let you build faster and more for the same amount of effort. But you aren't building, your LLM is. Also, you are only thinking about ways as you, a supposed builder, will benefit from this technology. Have you considered how all previous waves of new technologies have introduced downstream effects that have muddied our societies? LLMs are not unique in this regard, and…

Would you say the general contractor for your home isn’t a builder because he didn’t install the toilets?

Re: How I write software with LLMs

#326

Post by bigblind » Mon, Mar 16, 2026, 2:38 PM UTC

mlnj wrote: post #307

bigblind wrote: post #303

> On projects where I have no understanding of the underlying technology (e.g. mobile apps), the code still quickly becomes a mess of bad choices. However, on projects where I know the technologies used well (e.g. backend apps, though not necessarily in Python), this hasn’t happened yet, even at tens of thousands of SLoC. Most of that must be because the models are getting better, but I think that a lot of it is also…

Is that not already possible with Markdown spec files and planning mode?

I guess? At least there you can review the plan, but is this planning mode any better at making architectural decisions than when you prompt an LLM and let it make the changes directly? (it might be, just not sure.)

Re: How I write software with LLMs

#327

Post by _heimdall » Mon, Mar 16, 2026, 2:39 PM UTC

Havoc wrote: post #92

akhrail1996 wrote: post #22

Genuine question: what's the evidence that the architect → developer → reviewer pipeline actually produces better results than just... talking to one strong model in one session? The author uses different models for each role, which I get. But I run production agents on Opus daily and in my experience, if you give it good context and clear direction in a single conversation, the output is already solid. The ceremony…

Yeah always seemed pretty sus to me to. At the same time I can see a more linear approach doing similar. Like when I ask for an implementation plan that is functional not all that different from an architect agent even if not wrapped in such a persona

Once model providers started releasing "reasoning" models, and later roles and multi-agent systems, it seemed pretty clear to me they are just automating the process of prompt engineering.

They track everything we all do in a chat, then learn the patterns that work and build them in. Rinse and repeat.

Re: How I write software with LLMs

#328

Post by hansonkd » Mon, Mar 16, 2026, 2:39 PM UTC

akhrail1996 wrote: post #22

Genuine question: what's the evidence that the architect → developer → reviewer pipeline actually produces better results than just... talking to one strong model in one session? The author uses different models for each role, which I get. But I run production agents on Opus daily and in my experience, if you give it good context and clear direction in a single conversation, the output is already solid. The ceremony…

Any of these abstractions are just temporary.

Re: How I write software with LLMs

#329

Post by jplusequalt » Mon, Mar 16, 2026, 2:39 PM UTC

petcat wrote: post #275

sarchertech wrote: post #270

Earlier quoted context omitted.

If you can’t understand the difference between a bug that will rarely cause a compiler encountering an edge case to generate a wrong instruction and an LLM that will generate 2 completely different programs with zero overlap because you added a single word to your prompt, then I don’t know what to tell you.

The point is that expert humans (the GCC developers) writing code (C++) that generates code (ASM) does not appear to be as deterministic as you seem to think it is.

Classic HN-ism. To focus on the semantics of a statement while ignoring the greater point in order to argue why someone is wrong.

Re: How I write software with LLMs

#330

Post by datsci_est_2015 » Mon, Mar 16, 2026, 2:43 PM UTC

raw_anon_1111 wrote: post #299

datsci_est_2015 wrote: post #293

Earlier quoted context omitted.

As a consumer of goods, I care quite a bit about many of the “hows” of those goods just as much as the “whats”. My home, which I own, for example, is very much a “what” that keeps me warm and dry. But the “how” of it was constructed is the difference between (1) me cursing the amateur and careless decision making of builders and (2) quietly sipping a cocktail on the beach, free of a care in the world. “How” doesn’t m…

Do you know how every nail was put into your house? Does the general contractor?

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 the “how” of building homes and how it affects homeowners. Especially relevant here because he seems to specialize in inspecting homes that are part of large developments where a single company builds out many homes very quickly and cuts tons of corners and makes the same mistakes repeatedly, kind of like LLM-generated code.