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

471–480 of 544 posts

Re: How I write software with LLMs

#471

Post by ugtr3 »

codeflo wrote: post #71

I know the argument I'm going to make is not original, but with every passing week, it's becoming more obvious that if the productivity claims were even half true, those "1000x" LLM shamans would have toppled the economy by now. Were are the slop-coded billion dollar IPOs? We should have one every other week.

On a serious note it would be great to run an experiment - get 20 people on here claiming 100x productivity, and let’s see what they muster up in 1 month working together.

I’m happy to put money in towards it ;)

Re: How I write software with LLMs

#472

Post by icedchai »

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.

An LLM might take 5 minutes, or 20 minutes, and still do the wrong thing. Rarely have I seen an LLM not "know what to do." A coworker told it to fix some unit tests, it churned away for a while, then changed a bunch of assert status == 200 to 500. Good news, tests pass now!

Re: How I write software with LLMs

#473

Post by ugtr3 »

zingar wrote: post #165
codeflo wrote: post #71

I know the argument I'm going to make is not original, but with every passing week, it's becoming more obvious that if the productivity claims were even half true, those "1000x" LLM shamans would have toppled the economy by now. Were are the slop-coded billion dollar IPOs? We should have one every other week.

Writing pieces of code that beat average human level is solved. Organizing that code is on its way to being solved (posts like this hint at it). Finding problems that people will pay money to have solved by software is a different entirely more complicated matter (tbh I doubt anyone could prove right now that this absolutely is or isn’t solvable - but given the change we’ve seen already I place no bets against AI). A…

“ Finding problems that people will pay money to have solved by software is a different entirely more complicated matter ”

Come on you’re taking the piss, surely.

Re: How I write software with LLMs

#474

Post by FiberBundle »

stavros wrote: post #354
FiberBundle wrote: post #245

Earlier quoted context omitted.

Pine Town [1], the "whimsical infinite multiplayer canvas of a meadow", also looks like pure slop. [1] https://pine.town/

What were you hoping to achieve with this comment?

To help readers view the content of the article with scepticism, given the results the advice in it seems to produce.

Re: How I write software with LLMs

#475

Post by youknownothing »

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 guess it's no coincidence that most of then people saying "LLMs are great for doing code" are non-developers...

Re: How I write software with LLMs

#476

Post by stavros »

FiberBundle wrote: post #474
stavros wrote: post #354

Earlier quoted context omitted.

What were you hoping to achieve with this comment?

To help readers view the content of the article with scepticism, given the results the advice in it seems to produce.

"Guys this writer must be terrible, I saw one of his books and the cover wasn't good".

Re: How I write software with LLMs

#477

Post by icedchai »

raw_anon_1111 wrote: post #298
mikeocool wrote: post #263

Earlier quoted context omitted.

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.

It very much does have to modify the binary it produced to create new code. The entire Linux kernel has an unstable ABI where you have to recompile your code to link to system libraries.

The Linux userspace ABI is actually quite stable and rarely changes. If this wasn't true, every time you installed a new kernel you'd have to upgrade / reinstall everything else, including the C compiler, glibc, etc. This does not happen.

The Linux kernel ABI (kernel modules, like device drivers) on the other hand, is unstable and closely tied to the kernel version. Most people do not write kernel modules, so generally not an issue. (I did, many years ago.)

Re: How I write software with LLMs

#478

Post by kody »

timdellinger wrote: post #315
pathikrit wrote: post #288

10-15 years ago HN was the place where everyone showed off their new shiny toys and people would jump over themselves to try some new framework or db or tool. Now, so much negative sentiment about AI coding. I bet if LLMs came 15 years ago, HN would be brimming with excitement. What happened?

The difference is that CEOs fired a lot of people, using "AI can replace human coders" as an excuse. Also: there are claims all over the headlines along the lines of "We built something amazing without human coders." Both claims are loud and are flooding the discussion, but under the hood it's mostly a slop disaster. So the negative sentiment is a natural response (and a dose of realism).

Mix in exhaustion from previous hype cycles (NFTs?) and folks pushing the narrative that if you currently write any code manually, you’re obsolete and it’s hard to not want to push back negatively. Even if you find the tech interesting/useful.

Re: How I write software with LLMs

#479

Post by raw_anon_1111 »

icedchai wrote: post #477
raw_anon_1111 wrote: post #298

Earlier quoted context omitted.

It very much does have to modify the binary it produced to create new code. The entire Linux kernel has an unstable ABI where you have to recompile your code to link to system libraries.

The Linux userspace ABI is actually quite stable and rarely changes. If this wasn't true, every time you installed a new kernel you'd have to upgrade / reinstall everything else, including the C compiler, glibc, etc. This does not happen. The Linux kernel ABI (kernel modules, like device drivers) on the other hand, is unstable and closely tied to the kernel version. Most people do not write kernel modules, so general…

Isn’t that the reason that Android phones have piss poor support after being released?

Re: How I write software with LLMs

#480

Post by marcus_holmes »

indigodaddy wrote: post #7
marcus_holmes wrote: post #4

Earlier quoted context omitted.

that reference you give is pretty dated now, based on a talk from August which is the Beforetimes of the newer models that have given such a step change in productivity. The key change I've found is really around orchestration - as TFA says, you don't run the prompt yourself. The orchestrator runs the whole thing. It gets you to talk to the architect/planner, then the output of that plan is sent to another agent, aut…

Can you bolt superpowers onto an existing project so that it uses the approach going forward (I'm using Opencode), or would that get too messy?

These are just skills, so you can add the skills to your setup and start using them whenever you like.
Post reply on HN