I have not done any vibe coding and have a question for those who have.
Uncategorized
20
Posts
14
Posters
101
Views
-
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?
@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 -
@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@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
-
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?
@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).
-
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?
@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. 🪄 -
@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
@davew now if you want to see full code implementation of existing specs into a plugin for indiekit made entirely with Claude Code
- microsub : https://github.com/rmdes/indiekit-endpoint-microsub
- ActivityPub https://github.com/rmdes/indiekit-endpoint-activitypub are good candidate, they both went from reading the specs to full blown implementation after dozens of rounds of testing and incremental changes -
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?
@davew I wouldn't recommend it. It's trained on certain practices that are often not the best. Also refactoring custom, older code usually just means non working new code that might follow some patterns but doesn't work. Yep. It can even create test (unit test) that will clear up your (hopefully dev) database. So moderate success and often lots of frustration on the way.
(Antigravity and Gemini 3 and 3.1) -
@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).
@davew You can also augment the agent with specific skills where you explain things that may apply to a particular set of circumstances or only to a part of the project. The basic idea of those is that it has a small description of the skill loaded that tells it when to apply it -- and it then loads the details into the context when it needs them. I think that it's quite elegant for quite some things.
-
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?
@davew with the right instructions they can do the right thing. Did some big refactoring and swapping out libraries. The chance of success is higher depending on test coverage and good types
-
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?
@davew mostly breaks and that's why this part i still do manually…
-
@davew with the right instructions they can do the right thing. Did some big refactoring and swapping out libraries. The chance of success is higher depending on test coverage and good types
-
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?
@davew with the latest models (e.g. Claude Opus 4.6), actually surprisingly well. To the point where it makes writing a bunch of junk less of an issue since it can tidy up after itself surprisingly well
-
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?
@davew GPT 5 mini and Gemini via GitHub Copilot tend to pile on. Gemini models usually introduce extra variables or constants and add redundant comments to any code they can. I’ve resorted to mostly using agents for DevOps stuff (configuring Docker, etc.) and chats or edit mode for dealing with frustrating errors, messy code, or trivial yet tedious tasks. (almost all accidental alliteration always sounds advised)
-
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?
@davew Models with a larger context window should perform much better.
-
@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.
-
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?
@davew Whenever I am asking for something more complicated than simple, I first ask the machine to do a pre-mortem. I tell it to ask me questions and suggest things. Then, we go back and forth about everything. Only when I am satisfied, I let the machine generate the code for me. It happened that the machine suggested reorganizing the code or a a complete rewrite, and I approved it.
-
undefined davew@mastodon.social shared this topic on
Gli ultimi otto messaggi ricevuti dalla Federazione
-
@informapirata @informatica proprio non capisco secondo La commissione Europea in cosa una soluzione Cloud è meglio di una soluzione stand alon sul proprio computer.. come openoffice, per dirne uno
-
@stefano What a beautiful and well-written love letter. Well said.
-
255 – 3 clic per uccidere. Ecco il software che sceglie chi colpire https://www.camisanicalzolari.it/255-3-clic-per-uccidere-ecco-il-software-che-sceglie-chi-colpire/?utm_source=dlvr.it&utm_medium=mastodon
-
@phastidio
Oppure, accelerare gli investimenti del Green Deal contando sull'affidabile 'zampa' fossile della Norvegia.
-
Mi sono svegliata con un bel "sucacela forte" in testa da indirizzare al pazzoide che guida gli US.
Ora vuole l'aiuto NATO, per una guerra "sporca" che ha iniziato e voluto solo lui, facendo soltanto un favore al suo padrone Putin.
-
Trump ora vuole un intervento della NATO. In pratica, di un’istituzione basata sul diritto internazionale. Cioè su ciò che Trump è impegnato con tutte le proprie forze a distruggere dal suo primo giorno di mandato.
-
For me, FreeBSD is like vinyl.
Under <https://bsd.network/@rubenerd/116226243100921299> @rubenerd I wrote:
"there's no universally-accepted single explanation for the enduring popularity"
It's OK to like it, or love it, and no-one can authoritatively tell you that you're wrong to do so.
I mean, they can tell you that you're wrong, but ultimately: it's about what pleases the listener.
I mean, what pleases the user.
-
Why I love FreeBSD
A personal reflection on my first encounter with FreeBSD in 2002, how it shaped the way I design and run systems, and why its philosophy, stability, and community still matter to me more than twenty years later.
