Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

150k lines of vibe coded Elixir: The good, the bad and the ugly

getboothiq.com

Post reply on HN
Print view View original

81–90 of 91 posts

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#81

Post by CyberDildonics »

deadbabe wrote: post #23

Everyone always ends these articles with “I expect it will get better” What if it doesnt? What if LLMs just stay mostly the same level of usefulness they are now, but the costs continue to rise as subsidization wears off? Is it still worth it? Maybe, but not worth abandoning having actual knowledge of what you’re doing.

If it's not working now when extravagant amounts of money are being put into it, it might be time to just accept what it is and work around that instead of keeping all the grand predictions.

Anyone can sell the future.

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#82

Post by deadbabe »

CyberDildonics wrote: post #81
deadbabe wrote: post #23

Everyone always ends these articles with “I expect it will get better” What if it doesnt? What if LLMs just stay mostly the same level of usefulness they are now, but the costs continue to rise as subsidization wears off? Is it still worth it? Maybe, but not worth abandoning having actual knowledge of what you’re doing.

If it's not working now when extravagant amounts of money are being put into it, it might be time to just accept what it is and work around that instead of keeping all the grand predictions. Anyone can sell the future.

All the money in the present has been taken, you can now only make money from the future.

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#83

Post by pdimitar »

pmontra wrote: post #11

> In Elixir tests, each test runs in a database transaction that rolls back at the end. Tests run async without hitting each other. No test data persists. And it confuses Claude. This way of running tests is also what Rails does, and AFAIK Django too. Tests are isolated and can be run in random order. Actually, Rails randomizes the order so if the are tests that for any reason depend on the order of execution, they w…

I use Claude Opus and it gets the idea of Elixir's Ecto DB test case isolation through ultimately-rolled-back transactions just fine, FWIW.

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#85

Post by tossandthrow »

ogig wrote: post #66
tossandthrow wrote: post #52

Earlier quoted context omitted.

What is your secret sauce? How do you organize your project?

I decided to really learn what is going on, started with: https://karpathy.ai/zero-to-hero.html That give a useful background into understanding what the tool can do, what context is, and how models are post trained. Context management is an important concept. Then I gave a shot to several tools, including copilot and gemini, but followed the general advice to use Claude Code. It's way better that the rest at the mom…

Thanks! Very valuable insights.

I have been through Karpathy's work - however, I don't find that it helps with large scale development.

Your tactics work successfully for me at smalle scale (at around 10klocs, etc) and starts to break down - especially when refactorings are involved.

Refactoring happens when I see that the LLM is stumbling over it's own decisions _and_ when I get a new idea. So the ability to refactor is a hard requirement.

Alternatively refactoring could be achieved by starting over? But I do have a hard time accepting that idea for projects > 100klocs.

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#86

Post by barkerja »

ch4s3 wrote: post #45
barkerja wrote: post #26

Earlier quoted context omitted.

Opus 4.5 with Elixir has been remarkably good for me. I've been writing Elixir in production since ~2018 and it continues to amaze me at the quality of code it produces. I've been tweaking my skills to avoid nested cases, better use of with/do to control flow, good contexts, etc.

I'll have to check it out. I've found GPT to be adequate at producing running code that I can improve either by hand, or very specific prompting. What does your workflow look like?

I don't have a fancy workflow per se, but I have started leaning into git workspaces more which has really been a boon with Elixir (especially in large projects where compile times can be in the many tens of seconds).

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#87

Post by andnand »

Ronsenshi wrote: post #31
phplovesong wrote: post #22

"It writes 100% of our code" - Silently closes the tab, and makes a remark to avoid given software at any cost.

You're not missing much. Seems to me like they wrote 150k lines of code for some glorified photo app with ChatGPT in the backend for image processing. Oh and some note-taking it seems.

I was confused by this. Watching the demos on their page, it looks extremely slow. And it just does some image recognition to fill a form?

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#89

Post by esafak »

idle_zealot wrote: post #70
esafak wrote: post #34

Earlier quoted context omitted.

Think of it as 60 man-years of work.

If that's true then I can ship 60 man-years of work with yes 'println("a very important and useful line of code");' >> main.c in under a second!

How is that 60 man-years of work? You are not going to replicate what the LLM generated in under a second without the LLM.

Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly

#90

Post by cpursley »

barkerja wrote: post #43
cpursley wrote: post #30

Earlier quoted context omitted.

Try these: - https://github.com/agoodway/.claude/blob/main/skills/elixir-... - https://github.com/agoodway/.claude/blob/main/agents/elixir-... - https://github.com/agoodway/.claude/blob/main/agents/elixir-... Getting pretty good results so far.

These should get added to https://skills.sh/?q=elixir

https://skills.sh/agoodway/.claude/elixir-genius
Post reply on HN