I have not done any vibe coding and have a question for those who have.

[davew@mastodon.social]

I have not done any vibe coding and have a question for those who have.

Suppose you request a change, adding features, changing things around based on learning and testing, which is generally what happens after you've been working on something new.

Here's the question. What happens when you ask for a change that requires the codebase to be reorganized.

How did that go? Do the AIs know that's possible or do they just pile on special cases?

[konrad@fedi.neuwirth.priv.at]

@davew You can have them reorganize and refactor. With moderate success, I would say.

[ben@werd.social]

@davew I've experimented a little because I feel like I need to know how it works -

The older models would do insane stuff. Absolutely they would consider piling on special cases.

The latest models? It's genuinely a bit like magic. They don't always work but they will often reorganize and optimize a codebase - in a way that makes sense and actually works.

[davew@mastodon.social]

@konrad

heh, i was sure you could ask. 🙂

i'm doing a slow corner turn on some complex software to have it work in a different environment from which it was envisioned running in.

there's going to be new code at the top level, a combination of forking and factoring.

and done SLOWLY, considering all the problems, and not wanting to introduce any more complexity than i have to, to make future corner-turns more likely to work and not require wholesale rewrite.

does the bot know about this?

[cameronbanga@mastodon.social]

I’ve found that the key is the “context window”, which is a magic black box of what the app has been working on for the current session.

If I keep the tool focused on what I’ve been working on in the context window, the results have been pretty good. If I ask it to assess something it hasn’t touched, results get more wild.

[rmdes@indieweb.social]

@davew I have found that using Obra Superpower plugin/skills is of immense help to do just that, the first thing is to have claude code to map the repo and differentiate between instruction for him in Claude.md and for humans in readme.md
once the repo is properly described and mapped for claude you have your init context right, then for a refactoring or reorg of the code I would use an agent code reviewer to plan (superpower skill) and then only execute the plan once reviewed

[rmdes@indieweb.social]

@davew I have tested this approach both at work on a big legacy java repo which contained production code and dev spaghetis code lying around and to refactor personal code projects that I had initially developed with the help of chatgpt, with claude code I refactored and modernized all my custom python apps, it went really smooth, in both case I had to baby sit the process but the result was worth it

[konrad@fedi.neuwirth.priv.at]

@davew My personal experience is only with Claude Code so far, and with it, the current state of things is to first have it make a plan that also details its “understanding” of the code base. That then you can edit and adapt, and only then let it make actual changes. You can even use different models for the different tasks and my configuration specifies to think hard on the planning phase (using more context).

[drwhitt@mastodon.social]

@davew It’s been a mixed bag for me but mostly leans towards success. :) As suggested above, maintaining context with the tools is the key factor.

Sometimes, responses to follow-up prompts often include snippets of code that, while correct, can sometimes be hard to see where they need to be applied as a change/addition/subtraction. I find myself prompting to, “Please provide the complete implementation with this update included.” and that (almost always) works.

It does feel magical,
though. 🪄