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

491–500 of 544 posts

Re: How I write software with LLMs

#491

Post by bhaak »

LogicFailsMe wrote: post #351
bhaak wrote: post #317

Earlier quoted context omitted.

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.

Smart is not equal to intelligent.

You can be very intelligent but have a blind eye on some trivial things.

I’m certain that some of them think they are untouchable (or even just are well prepared). We will only see if that’s really true if shit hits the fan.

Re: How I write software with LLMs

#492

Post by avnsv »

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…

Using different models for the architect and developer roles isn't necessarily better because each model's solution lives in a different vector space. So when the architect (model A) produces a solution, the developer (model B) will implement the solution based on a different "mental map". So you may end up with a gap.

I normally use the same model (e.g. Codex 5.3) for planning, implementation, and testing, and then have another model (e.g. Opus 4.6) review the result to identify any issues and edge cases the developer didn't foresee and the tester didn't spot. Then I take the output and pass it back to the developer model to have it fix the issues.

Re: How I write software with LLMs

#493

Post by nvardakas »

BloondAndDoom wrote: post #467
nvardakas wrote: post #91

Earlier quoted context omitted.

[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?

[dead]

Re: How I write software with LLMs

#494

Post by xhale »

stavros wrote: post #429
kkarolis wrote: post #424

Earlier quoted context omitted.

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!

Thanks! (btw you have a typo on the second reviewer in the architect file. Is opencode smart enough to figure out the correct one?)

Re: How I write software with LLMs

#495

Post by theshrike79 »

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]

Agentic pipelines and systems fall into the same issues as humans who work together, mostly communication.

It's not like they can dump their full context to the "manager" agent, they need to condense stuff, which will result in misinterpreted information or missing information on decisions down the line.

IMO this was more relevant when agents had limited context windows

Re: How I write software with LLMs

#496

Post by IanCal »

> I’m planning to write something about this too, but this one is more of an art piece: It’s a ticking wall clock that ticks seconds irregularly, but is always accurate to the minute (with its time getting synced over the internet). It has various modes, one mode has variable tick timing, from 500 ms to 1500 ms, which is delightfully infuriating. Another mode ticks imperceptibly more quickly than a second, but then pauses for a second randomly, making the unsuspecting observer question their sanity. Another one races to :59 at double speed and then waits there for thirty seconds, and the last one is simply a normal clock, because all the irregular ticking drives me crazy.

I like this, I've always had a soft spot for interesting clocks, and the first description has a strong nostalgia for me from the Discworld:

> Someone very clever—certainly someone much cleverer than whoever had trained that imp—must have made the clock for the Patrician’s waiting room. It went tick-tock like any other clock. But somehow, and against all usual horological practice, the tick and the tock were irregular. Tick tock tick…and then the merest fraction of a second longer before…tock tick tock…and then a tick a fraction of a second earlier than the mind’s ear was now prepared for. The effect was enough, after ten minutes, to reduce the thinking processes of even the best-prepared to a sort of porridge. The Patrician must have paid the clockmaker quite highly.

Re: How I write software with LLMs

#497

Post by IanCal »

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)

> what kind of team lead is this?

One that trusts the team?

Knowing what's happening in the team and personally reviewing parts of the code for best practices are very different things. Are the other team members happy? Does development seem to go smoothly, quickly and without constantly breaking? Does the team struggle to upgrade or refactor things? At some level you have to start trusting that the people working know what they're doing, and help guide from a higher level so they understand how to make the right tradeoffs for the business.

Re: How I write software with LLMs

#498

Post by stavros »

xhale wrote: post #494
stavros wrote: post #429

Earlier quoted context omitted.

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

Thanks! (btw you have a typo on the second reviewer in the architect file. Is opencode smart enough to figure out the correct one?)

Hm I'll look, thanks! Yeah, it seems to work fine regardless.

Re: How I write software with LLMs

#499

Post by throwawayffffas »

arialdomartini wrote: post #68
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…

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…

I think the benefit may be task separation and cleaning the context between tasks. Asking a single session to do all three has a couple of downsides.

1. The context for each task gets longer, which we know degrades performance.

2. In that longer context, implicit decisions are made in the thinking steps, the model is probably more likely to go through with bad decisions that were made 20 steps back.

The way Stavros does it, is Architect -> Dev -> Review. By splitting the task in three sessions, we get a fresh and shorter context for each task. At minimum skipping the thinking messages and intermediary tool output, should increase the chances of a better result.

Using different agent personas and models at least introduces variability at the token generation, whether it's good or bad, I do not know. As far as I know in general it's supposed to help.

Having the sessions communicate I think is a mistake, because you lose all of the benefits of cleaning up the context, and given the chattiness of LLMs you are probably going to fill up the context with multiple thinking rounds over the same message, one from the session that outputs the message and one from the session reading the message, you are probably going to have competing tool uses, each session using it's own tool calls to read the same content, it will probably be a huge mess.

The way I do it is I have a large session that I interact with and task with planning and agent spawning. I don't have dedicated personas or agents. The benefits the way I see them are I have a single session with an extensive context about what we are doing and then a dedicated task handler with a much more focused context.

What I have seen with my setup is, impressively good performance at the beginning that degrades as feedback and tweaks around work pile up.

Re: How I write software with LLMs

#500

Post by sarchertech »

LogicFailsMe wrote: post #487
sarchertech wrote: post #482

Earlier quoted context omitted.

I bet you have ex-Amazon prominently in your LinkedIn profile.

Don't have a LinkedIn profile, don't need one. But I'm guessing you're listed under LinkedIn Lunatics.

I read back through a few of your posts and you’re either schizophrenic, or a very elaborate troll.

I know a few older people who started posting like this when they hit their 50s. I’ve only got a few years left. Hopefully I can avoid it, but maybe it’s inevitable.

Post reply on HN