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

421–430 of 544 posts

Re: How I write software with LLMs

#421

Post by bigfishrunning »

anthonyrstevens wrote: post #375
sweaterkokuro wrote: post #319

Earlier quoted context omitted.

In my experience its in all Language Models' nature to maximize token generation. They have been natively incentivized to generate more where possible. So if you dont put down your parameters tightly it will let loose. I usually put hard requirements of efficient code (less is more) and it gets close to how I would implement it. But like the previous comments say, it all depends on how deeply you integrate yourself i…

>> They have been natively incentivized to generate more where possible Do you have any evidence of this?

The cloud providers charge per output token, so aren't they then incentivized to generate as many tokens as possible? The business model is the incentive.

Re: How I write software with LLMs

#424

Post by kkarolis »

stavros wrote: post #210
xhale wrote: post #23

Hi, anyone has a simple example/scaffold how to set up agents/skills like this? I’ve looked at the stavrobots repo and only saw an AGENTS.md. Where do these skills live then? (I have seen obra/superpowers mentioned in the comments, but that’s already too complex and with an ui focus)

These skills live in my home directory, that's why they aren't in the repos. I can upload them if you want.

Not original commenter, but would be curious (and thankful) to see it.

Re: How I write software with LLMs

#425

Post by arikrahman »

keeda wrote: post #403
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 dunno, I have extensive experience reviewing code, and I still review all the AI generated code I own, and I find nothing to complain about in the vast majority of cases. I think it is based on "holding it right." For instance, I've commented before that I tend to decompose tasks intended for AI to a level where I already know the "shape" of the code in my head, as well as what the test cases should look like. So r…

"Holding it right" has been one of my biggest problems. Many times I find the output affected by prompt poisoning, and I have to throw away the entire context.

Re: How I write software with LLMs

#426

Post by TheMuenster »

never_inline wrote: post #138
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 this is just anthropomorphism. Sub agents make sense as a context saving mechanism. Aider did an "architect-editor" split where architect is just a "programmer" who doesn't bother about formatting the changes as diff, then a weak model converts them into diffs and they got better results with it. This is nothing like human teams though.

Absolutely agree with this. The main reason for this improving performance is simply that the context is being better controlled, not that this approach is actually going going to yield better results fundamentally.

Some people have turned context control into hallucinated anthropomorphic frameworks (Gas Town being perhaps the best example). If that's how they prefer to mentally model context control, that's fine. But it's not the anthropomorphism that's helping here.

Re: How I write software with LLMs

#427

Post by druide67 »

k3nx wrote: post #398
jplusequalt wrote: post #320

Earlier quoted context omitted.

>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…

I've struggled a bit with this myself. I'm having a paradigm shift. I used to say "but I like writing code". But like the article says, that's not really true. I like building things, the code was just a way to do that. If you want to get pedantic, I wasn't building things before AI either, the compiler/linker was doing that for me. I see this is just another level of abstraction. I still get to decide how things wor…

This resonates. I spent years thinking I enjoyed coding, but what I actually enjoy is designing elegant solutions built on solid architecture. Inventing, innovating, building progressively on strong foundations. The real pleasure is the finished product (is it ever really finished though?) — seeing it's useful and makes people's lives easier, while knowing it's well-built technically. The user doesn't see that part, but we know.

With AI, by always planning first, pushing it to explore alternative technical approaches, making it explain its choices — the creative construction process gets easier. You stay the conductor. Refactoring, new features, testing — all facilitated. Add regular AI-driven audits to catch defects, and of course the expert eye that nothing replaces.

One thing that worries me though: how will junior devs build that expert eye if AI handles the grunt work? Learning through struggle is how most of us developed intuition. That's a real problem for the next generation.

Re: How I write software with LLMs

#428

Post by stavros »

dncornholio wrote: post #312
stavros wrote: post #224

Earlier quoted context omitted.

Remember you're grinding your anti-LLM axe against something a real person made, and that person read your comment.

Don't think it's fair to think any negative comment is from some anti-LLM-axe. I seriously gave you the benefit of the doubt, that was the whole reason I even looked further into your work. It's no shame to be critical in todays world. Delivering proof is something that holds extra value and if I would create an article about the wonderful things I've created, I'd be extra sure to show it. I looked at your clock proj…

Saying things like "there's no proof of your work" is the anti-LLM axe. Yes, it's all written by LLMs, and yes, it's all my work. Judge it on what it does and how well it works, not on whether the code looks like the code you would have written.

Re: How I write software with LLMs

#429

Post by stavros »

kkarolis wrote: post #424
stavros wrote: post #210

Earlier quoted context omitted.

These skills live in my home directory, that's why they aren't in the repos. I can upload them if you want.

Not original commenter, but would be curious (and thankful) to see it.

I've updated the post with them, let me know if they work!

Re: How I write software with LLMs

#430

Post by LogicFailsMe »

raw_anon_1111 wrote: post #418
LogicFailsMe wrote: post #417

Earlier quoted context omitted.

Oh you're preaching to the choir. I think we are entering a punctuated equilibrium here w/r to the future of SW engineering. And the people who have the free time to go on to podcasts and insist AI coding agents can't do anything useful rather than learning their abilities and their limitations and especially how to wield them are going to go through some things. If you really want to trigger these sorts, ask them wh…

I haven’t stayed relevant and able to find jobs quickly for 30 years by being the old man shouting at the clouds. I started my career in 1996 programming in C and Fortran on mainframes and got my first only and hopefully last job at BigTech at 46 7 jobs later. I’m no longer there. Every project I’ve had in the last two years has had classic ML and then LLMs integrated into the implementation. I have very much jumped…

Started mine around the same time and yes, keeping up keeps one employed. What's disheartening however is how little keeping up the key decision makers and stakeholders at FAANNG do and it explains idiocy like already trying to fire engineers and replace them with AI. Hilarity ensued of course because hilarity always ensues for people like that, but hilarity and shenanigans appears to be inexhaustible resources.
Post reply on HN