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

381–390 of 544 posts

Re: How I write software with LLMs

#381

Post by seunosewa »

mikkupikku wrote: post #292
ruszki wrote: post #257

Earlier quoted context omitted.

Do they? I’ve never got a response that something was impossible, or stupid. LLMs are happy to verify that a noop does nothing, if they don’t know how to fix something. They rather make something useless than really tackle a problem, if they can make tests green that way, or they can claim that something “works”. And’ve I never asked Claude Code something which is really impossible, or even really difficult.

Claude code will happily tell me my ideas are stupid, but I think that's because I nest my ideas in between other alternative ideas and ask for an evaluation of all of them. This effectively combats the sycophantic tendencies. Still, sometimes claude will tell me off even when I don't give it alternatives. Last night I told it to use luasocket from an mpv userscript to connect to a zeromq Unix socket (and also implem…

After such hard-won wins, ask the AI to save what it learned during the session to a MD file.

Re: How I write software with LLMs

#382

Post by tracker1 »

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…

Yeah, the more time I spend in planning and working through design/api documentation for how I want something to work, the better it does... Similar for testing against your specifications, not the code... once you have a defined API surface and functional/unit tests for what you're trying to do, it's all the harder for AI to actually mess things up. Even more interesting is IMO how well the agents work with Rust vs other languages the more well defined your specifications are.

Re: How I write software with LLMs

#383

Post by sarchertech »

anthonyrstevens wrote: post #362
sarchertech wrote: post #336

Earlier quoted context omitted.

If you don't understand the difference between something that rigorously translates one formal language to another one and something that will spit out a completely different piece of software with 0 lines of overlap based on a one word prompt change, I don't know what to tell you.

"rigorously" is doing a lot of heavy lifting here.

Let's substitute rigorously with "in an extremely thorough, careful, and methodical way."

Re: How I write software with LLMs

#384

Post by dkersten »

petcat wrote: post #242
zackify wrote: post #239

Earlier quoted context omitted.

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…

If you tell a human junior developer just "fix this" then they will spend a week on a wild-goose chase with nothing to show for it. At least the LLM will only take 5 minutes to tell you they don't know what to do.

> At least the LLM will only take 5 minutes to tell you they don't know what to do.

In my experience, the LLM will happily try the wrong thing over and over for hours. It rarely will say it doesn’t know.

Re: How I write software with LLMs

#385

Post by sarchertech »

raw_anon_1111 wrote: post #340
sarchertech wrote: post #337

Earlier quoted context omitted.

It has nothing to do with determinism. It's the difference between nearly perfectly but not quite perfectly translating between rigorously specified formal languages and translating an ambiguous natural language specification into a formal one. The first is a purely mechanical process, the second is not and requires thousands of decisions that can go either way.

And that’s no different than human developers

The difference is that a human is that a human can reason about their code changes to a much higher degree than an AI can. If you don't think this is true and you think we're working with AGI, why would you bother architecting anything all or building in any guard rails. Why not just feed the AI the text of the contract your working from and let it rip.

Re: How I write software with LLMs

#386

Post by sarchertech »

LogicFailsMe wrote: post #357
sarchertech wrote: post #334

Earlier quoted context omitted.

>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'l…

What are you even arguing about? I have absolutely no idea where you are going with this.

Re: How I write software with LLMs

#387

Post by tracker1 »

mbesto wrote: post #282
zackify wrote: post #239

Earlier quoted context omitted.

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…

> Its shocking some people don't give it any real instruction or way to check itself. It's not shocking. The tech world is telling them that "Claude will write all of their app easily" with zero instructions/guidelines so of course they're going to send prompts like that.

I think the implications of limited to no instructions are a little to way off depending on what you're doing... CRUD APIs, sure... especially if you have a well defined DB schema and API surface/approach. Anything that might get complex, less so.

Two areas I've really appreciated LLMs so far... one is being able to make web components that do one thing well in encapsulation.. I can bring it into my project and just use it... AI can scaffold a test/demo app that exercises the component with ease and testing becomes pretty straight forward.

The other for me has been in bridging rust to wasm and even FFI interfaces so I can use underlying systems from Deno/Bun/Node with relative ease... it's been pretty nice all around to say the least.

That said, this all takes work... lots of design work up front for how things should function... weather it's a ui component or an API backend library. From there, you have to add in testing, and some iteration to discover and ensure there aren't behavioral bugs in place. Actually reviewing code and especially the written test logic. LLMs tend to over-test in ways that are excessive or redundant a lot of the time. Especially when a longer test function effectively also tests underlying functionalities that each had their own tests... cut them out.

There's nothing "free" and it's not all that "easy" either, assuming you actually care about the final product. It's definitely work, but it's more about the outcome and creation than the grunt work. As a developer, you'll be expected to think a lot more, plan and oversee what's getting done as opposed to being able to just bang out your own simple boilerplate for weeks at a time.

Re: How I write software with LLMs

#388

Post by staticassertion »

borski wrote: post #371
staticassertion wrote: post #238

Earlier quoted context omitted.

It's well understood that programming interviews are a pretty shitty tool. They're a proxy for understanding if you have basic skills required to understand a computer. Notably, most companies don't rely on these alone, they have behavioral questions, architecture questions, etc. Have you ever done an interview at these companies you're talking about? They're 8 hours lol maybe 1 is spent programming. But it's just ve…

Yeah, this is precisely what I meant.

I'm genuinely blown away at the attitude lately that developers spend their time programming/ our primary value is code. I guess because we tend to be organizationally isolated people just have no idea? But like... it's so absurd to anyone who does the job. It's like thinking that PM's primary role is assigning tickets, just so obviously false.

I think there's some resentment. I've seen repeatedly now people essentially celebrating that "tech bros" are finally going to see their salaries crash or whatever, it's pretty sick but I've noticed this quite a lot.

Re: How I write software with LLMs

#390

Post by Ancapistani »

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…

> complain they aren't getting great results without a lot of hand holding

This is what I don’t understand - why would I “complain” about “hand holding”? Why would I just create a Claude skill or analogue that tells the agent to conform to my preferences?

I’ve done this many times, and haven’t run into any major issues.

Post reply on HN