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

Give Django your time and money, not your tokens

better-simple.com

Post reply on HN
Print view View original

21–30 of 184 posts

Re: Give Django your time and money, not your tokens

#21

Post by Cpoll »

comboy wrote: post #18

Perhaps we should start making LLM- open source projects (clearly marked as such). Created by LLMs, open for LLM contributions, with some clearly defined protocols I'd be interesting where it would go. I imagine it could start as a project with a simple instruction file to include in your project to try to find abstractions which can be useful to others as a library and look for specific kind of libraries. Some peopl…

Moltbook meets GitHub? Sounds like a billion dollar valuation (sarcasm tag deliberately omitted).

Re: Give Django your time and money, not your tokens

#22

Post by boxed »

yuppiepuppie wrote: post #3

I love Django. Ive been using it professionally and on side projects extensively for the past 10 years. Plus I maintain(ed) a couple highly used packages for Django (django-import-export and django-dramatiq). Last year, I had some free time to try to contribute back to the framework. It was incredibly difficult. Difficult to find a ticket to work on, difficult to navigate the codebase, difficult to get feedback on a…

I picked up a change that had broad consensus and quite a bit of excitement over even by some core devs.

That ticket now just sits there. The implementation is done, the review is done, there are no objections. But it's not merged.

I think something is deeply wrong and I have no idea what it is.

Re: Give Django your time and money, not your tokens

#23

Post by boxed »

a4isms wrote: post #17
readitalready wrote: post #5

[flagged]

> Django in particular is optimized for LLMs Meanwhile, a different take: Now, what we’ve been told about models is that they’re only as good as their training data. And so languages with gargantuan amounts of training data ought to fare best, right? Turns out that models kind of universally suck at Python and Javascript (comparatively). The top performing languages (independent of model) are C#, Racket, Kotlin, and…

I am using Claude Code with Elm, a very obscure language, and I find that it's amazing at it.

Re: Give Django your time and money, not your tokens

#25

Post by boxed »

positive-spite wrote: post #10
readitalready wrote: post #5

[flagged]

In that case I encourage you to build Django with your LLM of choice. Do what the Django team does, and be of service to the public! I challange you to prove that Django is sloppier than your LLM-Version

Someone beat you to it: https://github.com/mymi14s/openviper

Re: Give Django your time and money, not your tokens

#26

Post by yuppiepuppie »

boxed wrote: post #22
yuppiepuppie wrote: post #3

I love Django. Ive been using it professionally and on side projects extensively for the past 10 years. Plus I maintain(ed) a couple highly used packages for Django (django-import-export and django-dramatiq). Last year, I had some free time to try to contribute back to the framework. It was incredibly difficult. Difficult to find a ticket to work on, difficult to navigate the codebase, difficult to get feedback on a…

I picked up a change that had broad consensus and quite a bit of excitement over even by some core devs. That ticket now just sits there. The implementation is done, the review is done, there are no objections. But it's not merged. I think something is deeply wrong and I have no idea what it is.

Have you tried pinging in the Discord about it?

Re: Give Django your time and money, not your tokens

#29

Post by thewebguyd »

Cpoll wrote: post #21
comboy wrote: post #18

Perhaps we should start making LLM- open source projects (clearly marked as such). Created by LLMs, open for LLM contributions, with some clearly defined protocols I'd be interesting where it would go. I imagine it could start as a project with a simple instruction file to include in your project to try to find abstractions which can be useful to others as a library and look for specific kind of libraries. Some peopl…

Moltbook meets GitHub? Sounds like a billion dollar valuation (sarcasm tag deliberately omitted).

Actually, I'd want to see that. All the AI companies keep saying it will take our jobs, human developers won't be necessary.

Well let them put their money where their mouth is. Let's see what happens, see what the agents create or fail to create. See if we end up with a new OS, kernel all the way up to desktop environment.

Re: Give Django your time and money, not your tokens

#30

Post by gedy »

yuppiepuppie wrote: post #3

I love Django. Ive been using it professionally and on side projects extensively for the past 10 years. Plus I maintain(ed) a couple highly used packages for Django (django-import-export and django-dramatiq). Last year, I had some free time to try to contribute back to the framework. It was incredibly difficult. Difficult to find a ticket to work on, difficult to navigate the codebase, difficult to get feedback on a…

I agree somewhat, as I deal with an internal legacy codebase that's pretty hard to follow, and I use Gemini, Claude, etc to help learn, debug solutions and even propose solutions. But there's a big difference in using it as a learning tool and just having the LLM "do it". I see little value in first time contributors just leaning on an LLM to just do it.
Post reply on HN