←back to thread

A Software Development Methodology for Disciplined LLM Collaboration

(github.com)
97 points jay-baleine | 2 comments | 06 Sep 25 10:47 UTC | HN request time: 0s | source
Show context
sublinear ◴[06 Sep 25 12:58 UTC] No.45148898[source]▶
This may produce some successes, but it's so much more work than just writing the code yourself that it's pointless. This structured way of working with generative AI is so strict that there is no scaling it up either. It feels like years since this was established to be a waste of time.

If the goal is to start writing code not knowing much, it may be a good way to learn how and establish a similar discipline within yourself to tackle projects? I think there's been research that training wheels don't work either though. Whatever works and gets people learning to write code for real can't be bad, right?

replies(3): >>45148990 #>>45149237 #>>45149588 #
1. weego ◴[06 Sep 25 13:10 UTC] No.45148990[source]▶
It's just a function of how much code you need to write, and how much un-interrupted time you have.

Editing this kind of configuration has far less cognitive load and loading time, so distractions aren't as destructive to the task as they are when coding. You can then also structure time so that productive agent coding can be happening while you're doing business critical tasks like meetings / calls etc.

I do think this is overkill though, and it's a bad plan and far too early to try and formalize The One Way To Instruct AI How To Code, but every advance is an opportunity to gain career traction so fair play.

replies(1): >>45160714 #
2. wheelerwj ◴[07 Sep 25 18:10 UTC] No.45160714[source]▶
> Editing this kind of configuration has far less cognitive load and loading time, so distractions aren't as destructive to the task as they are when coding.

Very interesting observation!