Starting a community for coders&non-coders/AI-assisted plugin development

Explore how Machine Learning and AI can expand musical creativity while keeping the human in the creative workflow. This forum is dedicated to respectful dialogue where diverse perspectives are welcomed.
RELATED
PRODUCTS

Post

Teksonik wrote: Mon Mar 09, 2026 8:03 pmThey put in the long hours and hard work of learning how to properly code
Maybe but if they don't get on board with vibe coding with AI, they will be left in the dust by everyone else. Interestingly, it's apparently programmers who are most likely to be using AI and see it as a positive development within their industry. But they can't have it both ways, they can't see it as positive but want to have it all to themselves so I'll bet that your precious small developers are fine with others using AI.
so when someone comes along and brags about doing it the lazy way there are no words in the English language to convey my disdain for that person.
That's because you are a grumpy, ignorant, joyless bastard.
NOVAkILL : Legion GO, AMD Z1x, 16GB RAM, Win11 | Audient EVO 8 | Lumi Keys | Studio Pro 8
Korg Odyssey, bx-oberhausen, Proxima, PolyMax, GR8, JP6K, Union, Atomika,
Invader 2, Flow Motion, Olga, TRK 01, Thorn, Spire, VG Iron

Post

I'll give you a pretty good reason to not engage with vibe coding: because it does not work!

https://www.theregister.com/2026/03/17/ ... codestrap/
AI still doesn't work very well, businesses are faking it, and a reckoning is coming

Enterprise organizations are still struggling to figure out how AI fits into their business, and that may be for the best because it will take time to understand any problems caused by AI-generated code and content.

"No one knows right now what the right reference architectures or use cases are for their institution," said Dorian Smiley, co-founder and CTO of AI advisory service Codestrap, in an interview with The Register. "A lot of people are pretending that they know. But there's no playbook to pull from."

Smiley and his co-founder, CEO Connor Deeks, did time at global consultancy PwC and have set up their own shop to help shepherd organizations toward an AI strategy.

They argue that companies chasing AI have gotten ahead of themselves.

[...]

Measures of engineering excellence, said Smiley, include metrics like deployment frequency, lead time to production, change failure rate, mean time to restore, and incident severity. And we need a new set of metrics, he insists, to measure how AI affects engineering performance.

"We don't know what those are yet," he said. One metric that might be helpful, he said, is measuring tokens burned to get to an approved pull request – a formally accepted change in software. That's the kind of thing that needs to be assessed to determine whether AI helps an organization's engineering practice.

To underscore the consequences of not having that kind of data, Smiley pointed to a recent attempt to rewrite SQLite in Rust using AI.

"It passed all the unit tests, the shape of the code looks right," he said. It's 3.7x more lines of code that performs 2,000 times worse than the actual SQLite. Two thousand times worse for a database is a non-viable product. It's a dumpster fire. Throw it away. All that money you spent on it is worthless."
We are the KVR collective. Resistance is futile. You will be assimilated. Image
My MusicCalc is served over https!!

Post

What I would like to see, whether developed with AI assistance or not, is an environment with a modular DAW-like approach (energyXT is what I picture in my mind, but I’m sure there are modern examples), where you could chain open-source plugins together and tweak them, apply controls to certain parameters or combinations of parameters, apply a GUI, and export the project as a new customized open-source plugin. It would fill a roll similar to the roll provided by SynthEdit in the past. Quick prototypes, beginners’ playground…

Maybe such an app could have the ability to assist in gathering the open source code from GitHub, compiling it to be used as a plugins within its development environment, and then exporting the finished composite plugin in compliance with all applicable open-source licensing rules… bundle the source-code for the donor plugins used in creating the new plugin, required citations, put it all back on GitHub if desired.

All upfront and legitimate, it would actively help manage GitHub, or whatever, and dot all the i’s and cross all the t’s for you.

If such an environment could exist I think it would be a positive thing, especially at bringing in potential future developers, but also just as a fun option for musicians to explore effects in a different way and even create their own customized plugins.

Post

You can get a working app with vibe coding, but it might break any time in any environment, and if you dont know what you're doing, you will not be able to fix it.
Not sure why people could have a problem with AI assisted coding though. In any case, you need to review the code you get from anywhere, be it Stack Overflow or Claude Code, thoroughly. Developers usually are aware that they are responsible for the code no matter where it comes from.

Post Reply

Return to “Machine Learning and AI for Music Creation”