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

261–270 of 544 posts

Re: How I write software with LLMs

#261

Post by il-b »

ChrisGreenHeur wrote: post #159
ashwinsundar wrote: post #11

Earlier quoted context omitted.

Hot take: you can't have your cake and eat it too. If you aren't writing code, designing the system, creating architecture, or even writing the prompt, then you're not understanding shit. You're playing slots with stochastic parrots The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until i…

the hardware you typed this on was designed by hardware architects that write little to no code. just types up a spec to be implemented by verilog coders.

[dead]

Re: How I write software with LLMs

#262

Post by krilcebre »

petcat wrote: post #237
awakeasleep wrote: post #230

Earlier quoted context omitted.

Explain how fragility of implementation, like spaghetti code, high coupling low cohesion fit into your world view?

As human developers, I think we're struggling with "letting go" of the code. The code we write (or agents write) is really just an intermediate representation (IR) of the solution. For instance, GCC will inline functions, unroll loops, and myriad other optimizations that we don't care about (and actually want!). But when we review the ASM that GCC generates we are not concerned with the "spaghetti" and the "high coup…

You are comparing compilers to a completely non deterministic code generation tool that often does not take observable behavior into account at all and will happily screw a part of your system without you noticing, because you misworded a single prompt.

No amount of unit/integration tests cover every single use case in sufficiently complex software, so you cannot rely on that alone.

Re: How I write software with LLMs

#263

Post by mikeocool »

petcat wrote: post #237
awakeasleep wrote: post #230

Earlier quoted context omitted.

Explain how fragility of implementation, like spaghetti code, high coupling low cohesion fit into your world view?

As human developers, I think we're struggling with "letting go" of the code. The code we write (or agents write) is really just an intermediate representation (IR) of the solution. For instance, GCC will inline functions, unroll loops, and myriad other optimizations that we don't care about (and actually want!). But when we review the ASM that GCC generates we are not concerned with the "spaghetti" and the "high coup…

When requirements change, a compiler has the benefit of not having to go back and edit the binary it produced.

Maybe we should treat LLM generated code similarly —- just generate everything fresh from the spec anytime there’a a change, though personally I haven’t had much success with that yet.

Re: How I write software with LLMs

#264

Post by petcat »

sarchertech wrote: post #244
petcat wrote: post #237

Earlier quoted context omitted.

As human developers, I think we're struggling with "letting go" of the code. The code we write (or agents write) is really just an intermediate representation (IR) of the solution. For instance, GCC will inline functions, unroll loops, and myriad other optimizations that we don't care about (and actually want!). But when we review the ASM that GCC generates we are not concerned with the "spaghetti" and the "high coup…

A compiler uses rigorous modeling and testing to ensure that generated code is semantically equivalent. It can do this because it is translating from one formal language to another. Translating a natural prompt on the other hand requires the LLM to make thousands of small decisions that will be different each time you regenerate the artifact. Even ignoring non-determinism, prompt instability means that any small chan…

> A compiler uses rigorous modeling and testing to ensure that generated code is semantically equivalent.

Here are the reported miscompilation bugs in GCC so far in 2026. The ones labeled "wrong-code".

https://gcc.gnu.org/bugzilla/buglist.cgi?chfield=%5BBug%20cr...

I count 121 of them.

Re: How I write software with LLMs

#266

Post by datsci_est_2015 »

make_it_sure wrote: post #206
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…

you are overestimating the skill of code review. Some people have very specific ways of writing code and solving problems which are not aligned what LLMs wrote, but doesn't mean it's wrong. I know senior developers that are very radical on some nonsense patterns they think are much better than others. If they see code that don't follow them, they say it's trash. Even so, you can guide the LLM to write the code as you…

> 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 and forth with LLM-generated code makes me think that the marginal utility of a lot of code the strong proponents write is <1¢. If I fuck up my code, it costs our partners $200/hr per false alert, which obliterates the profit margin of using our software in the first place.

Re: How I write software with LLMs

#267

Post by sarchertech »

raw_anon_1111 wrote: post #253
sarchertech wrote: post #244

Earlier quoted context omitted.

A compiler uses rigorous modeling and testing to ensure that generated code is semantically equivalent. It can do this because it is translating from one formal language to another. Translating a natural prompt on the other hand requires the LLM to make thousands of small decisions that will be different each time you regenerate the artifact. Even ignoring non-determinism, prompt instability means that any small chan…

As if when you delegate tasks to humans they are deterministic. I would hope that your test cases cover the requirements. If not, your implementation is just as brittle when other developers come online or even when you come back to a project after six months.

1. Agents aren’t humans. A human can write a working 100k LOC application with zero tests (not saying they should but they could and have). An agent cannot do this.

Agents require tests to keep them from spinning out and your tests do not cover all of the behaviors you care about.

2. If you doubt that your tests don’t cover all your requirements, 99.9% of every production bug you’ve ever had completely passed your test suite.

Re: How I write software with LLMs

#268

Post by Levitating »

gehsty wrote: post #198

When I use Claude code to work on a hobby project it feels like doom scrolling… I can’t get my head around if the hobby is the making or the having, but fair to say I’ve felt quite dissatisfied at the end of my hobby sessions lately so leaning towards the former.

Agreed, I code for fun. But I am not sure if I still find it fun if the LLM just makes what I want.

Re: How I write software with LLMs

#269

Post by speakingmoistly »

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.

To be fair, that happening feels more like poor management and mentorship than "juniors are scatterbrained".

Over time, you build up the right reflexes that avoid a one-week goose chase with them. Heck, since we're working with people, you don't just say " fix this", you earmark time to make sure everyone is aligned on what needs done and what the plan is.

Re: How I write software with LLMs

#270

Post by sarchertech »

petcat wrote: post #264
sarchertech wrote: post #244

Earlier quoted context omitted.

A compiler uses rigorous modeling and testing to ensure that generated code is semantically equivalent. It can do this because it is translating from one formal language to another. Translating a natural prompt on the other hand requires the LLM to make thousands of small decisions that will be different each time you regenerate the artifact. Even ignoring non-determinism, prompt instability means that any small chan…

> A compiler uses rigorous modeling and testing to ensure that generated code is semantically equivalent. Here are the reported miscompilation bugs in GCC so far in 2026. The ones labeled "wrong-code". https://gcc.gnu.org/bugzilla/buglist.cgi?chfield=%5BBug%20cr... I count 121 of them.

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.
Post reply on HN