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

461–470 of 544 posts

Re: How I write software with LLMs

#461

Post by LogicFailsMe »

sarchertech wrote: post #455
LogicFailsMe wrote: post #408

Earlier quoted context omitted.

What's with all the catastrophic thinking then? Mad Max? Collapse of Society because 45% unemployment? I really hate people on principle but I have more faith in them looking out for their own self interest than you do apparently. Mad Max specifically requires a ridiculous amount of intact infrastructure for all the gasoline (you know gasoline goes bad in 3-6 months? Yeah didn't think so), manufacturing for all the p…

>Mad Max specifically requires a ridiculous amount of intact infrastructure for all the gasoline (you know gasoline goes bad in 3-6 months? Yeah didn't think so) Is this a joke or do you have a learning disability? >But I expect 24/7 IC3 level engineering as a service for $200/month to be more than enough and I think that's a year or two away. And you can either prepare for that or scream how the sky is falling, your…

I guess you have a really short context buffer with all this frequently forgetting things you've said yourself.

But that aside, how's all that self-righteousness working out for you?

Re: How I write software with LLMs

#462

Post by danbruc »

mbesto wrote: post #460
danbruc wrote: post #297

Earlier quoted context omitted.

I don't know, I would assume it works but I would not expect it to be free of bugs. But that is the baseline for code, being correct - up to some bugs - is the absolute minimum requirement, code quality starts from there - is it efficient, is it secure, is it understandable, is it maintainable, ...

So do you expect it not to be free of bugs because you've run a comprehensive test on it, read all of the code yourself or are you just concluding that because you know it was generated by an LLM?

It has not been formally verified which is essentially the only way to achieve code without defects with reasonable confidence. There are several studies that have found that there are roughly between one and twenty bugs per thousand lines of code in any software, this project has several thousand lines of code, so I would expect several bugs if written by humans and I have no reason to assume that large language models outperform humans in this respect, not at last because they are trained on code written by humans and have been trained to generate code as written by humans.

Re: How I write software with LLMs

#463

Post by northzen »

cpt_sobel wrote: post #80
raincole wrote: post #77

Earlier quoted context omitted.

Because some people like to be polite? Is it this hard to understand? Your hand-written prompts are unlikely to take significant chunk of context window anyway.

Polite to whom?

To machine. It just easier to be polite by default than split our language into two forms "I speak to human" and "I speak to machine". Because the chat interface is really close to what we see when we speak to human. Well, exactly the same.

Re: How I write software with LLMs

#464

Post by Miraste »

visarga wrote: post #452
Miraste wrote: post #444

Earlier quoted context omitted.

LLMs also don't have the primary advantage humans get from job separation, diverse perspectives. A council of Opuses are all exploring the exact same weights with the exact same hardware, unlike multiple humans with unique brains and memories. Even with different ones, Codex 5.3 is far more similar to Opus than any two humans are to each other. Telling an Opus agent to focus on security puts it in a different part of…

You can differentiate by context, one sees the work session, the other sees just the code. Same model, but different perspectives. Or by model, there are at least 7 decent models between the top 3 providers.

I know, but none of those is nearly as much of a difference as another human looking at code. The top models have such overlapping training data they sometimes identify as each other.

Re: How I write software with LLMs

#465

Post by xnx »

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…

We are at the horseless carriage stage where people are recreating the old system without considering if it is necessary.

Re: How I write software with LLMs

#466

Post by BloondAndDoom »

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…

I think many people don’t understand that you can just say check again to the model you use and it will just find bugs, repeat it until there are no bugs. Sounds stupid but it works. It’s intuitive to assume another will help more and better review but yeah I don’t know.

Also in my experience codex always writes better code and more sensible than Claude (but slower)

Re: How I write software with LLMs

#467

Post by BloondAndDoom »

nvardakas wrote: post #91
arialdomartini wrote: post #68

Earlier quoted context omitted.

This is anecdotal but just a couple days ago, with some colleagues, we conducted a little experiment to gather that evidence. We used a hierarchy of agents to analyze a requirement, letting agents with different personas (architect, business analyst, security expert, developer, infra etc) discuss a request and distill a solution. They all had access to the source code of the project to work on. Then we provided the v…

[dead]

Absolutely works with frontier models. What do you think about smaller models in these pipelines? That’s literally what I’m working on, with qwen3.5-27b and im splitting the task to 4 steps and not sure if that’s the way to go. Do you have any experience to share?

Re: How I write software with LLMs

#468

Post by BloondAndDoom »

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…

Also Claude (and possibly others) sometimes decide to build everything an obviously bad idea, shitty architecture then keeps doubling down into mess of a code. My realization is I need to be the manager architect, let it produce the plan then review and adjust the architecture. Once you get good control of architecture way may less bugs, and easier to fix. One final thing hook observability really early on and then force LLM to throw all exceptions instead of “safe fallbacks” which in practice means I will swallow everything a you. Will need look at all of the code every time there is bug.

Re: How I write software with LLMs

#469

Post by ugtr3 »

Rapzid wrote: post #401
sarchertech wrote: post #254

Earlier quoted context omitted.

> It doesn’t matter to AI whether the code is spaghetti code or not. What you said was only important when humans were maintaining the code. In my experience using AI to work on existing systems, the AI definitely performs much better on code that humans would consider readable. You can’t really sit here talking about architecting greenfield systems with AI using methodology that didn’t exist 6 months ago while confi…

> Well you can, and most consultants do tend to do that Yeah they do. I'm familiar enough with the claims to feel confident there is plenty of nefarious astroturfing occurring all over the web including on HN.

Indeed. Astro turfing posts have a particular smell to them.

Re: How I write software with LLMs

#470

Post by ugtr3 »

jbergqvist wrote: post #332

I've found that spending most of my time on design before any code gets written makes the biggest difference. The way I think about it: the model has a probability distribution over all possible implementations, shaped by its training data. Given a vague prompt, that distribution is wide and you're likely to get something generic. As you iterate on a design with the model (really just refining the context), the distr…

Yea but that design part is the most expensive part. The code generation is pretty trivial - the advantage of llm’s is the power to search through pre-trained information spaces - much faster than a human could. Issue is again.. probabilistic. So there’s variance.’
Post reply on HN