Loopy Pro: Create music, your way.
What is Loopy Pro? — Loopy Pro is a powerful, flexible, and intuitive live looper, sampler, clip launcher and DAW for iPhone and iPad. At its core, it allows you to record and layer sounds in real-time to create complex musical arrangements. But it doesn’t stop there—Loopy Pro offers advanced tools to customize your workflow, build dynamic performance setups, and create a seamless connection between instruments, effects, and external gear.
Use it for live looping, sequencing, arranging, mixing, and much more. Whether you're a live performer, a producer, or just experimenting with sound, Loopy Pro helps you take control of your creative process.
Download on the App StoreLoopy Pro is your all-in-one musical toolkit. Try it for free today.
Comments
Big tech companies shilled AI as a tool, but in reality, the public accepted it as an object. Why wouldn't they?!
Where is the vibe in vibe-coding when you are essentially serving some regurgitated generic code snippets to construct something called "my app" and you still don't have full insight into most of its code parts?
Meanwhile, your target customers, instead of wasting money on that app, can simply ask this same AI system for the desired outcome. 🤦♂️
Of course AI could be used as a tool; imho, every programmer dreams of a system that can draw you a graphical presentation of all class relations or crystallize data structure from your project, etc. There are countless ways you can use AI as a tool and have complete control over your code. 😌 But, this is talk for another thread...
At the point that we achieve fluency in our native tongue, we have been exposed to a lot of data but immensely less than an LLM requires to achieve the same mastery -- not just of understanding but also of producing original new utterances recognized by other native speakers as fluent.
No LLM that starts out untrained without pre-built algorithmic knowledge to jumpstart it will develop the ability to generate music nearly as sophisticate, coherent or original as music generated by someone like Mozart or Stevie Wonder given the amount of input data that they had.
The processes really are fundamentally different. We are fooled by the output and project backwards that the process must be the same -- and we get fooled by the technology being named after biological processes (neural net). Neural nets are an advancement over methods that preceded them and are inspired by aspects of biology -- but that is different from their being more similar than they are.
You (and most people in this thread) are still talking about small simple apps “vibecoded” by people with minimal or zero coding kniwledge in few days.
This is now hype, influencers are shilling it, it’s trendy to have own “app”.
This treand will soon die. Fade out. Those people will find new “big thing”. They realise there is not market for their shitty mini apps full of bugs and security holes which are bringing nithing new and there is 1000 other apps doing same thing. And especislly when at the end of this year prices of tokens and subscriptions for models will skyrocked, bubble bursts, no doubt about that.
But.
Can you even imagine what can do experienced coder with decades of coding experience and deep understanding in area in which app is developed (theoretic knowlede, math, etc), when he is working for MANY months or even year or so on some large scale app with this tool ?
i think most people have no idea what is possible in that setup. Literally limitless.
Of course there are differences. Nevertheless, a response to some of this by ChatGPT:
https://chatgpt.com/share/6a0dfee6-7b3c-83a4-b981-5d3874211811
Claude (Opus 4.7 / Adaptive thinking mode) generally agress with few notes to what GPT wrote
)
Well hence the youtube thumbnail earlier! That was kind of a case where an end user skipped the middleman sort of, though didn't watch the full video. No disagreement there (as far as it being a distinct possibility).
I even called out how the thread glossed over that little nugget - before taking my own advice about sitting this one out and redacting my wall of text
Oh no! Mere 2 lines after quoting "incorrectly postulated LLM overfitting as frequently used straw man"?
Dendy, I just followed the thread subject. 😌 In many communities vibe coding seems to be declining, while agentic engineering is the new big thing and who knows what else in the near future.
If you're talking about LLMs, we don't share the same enthusiasm. Can this technology be a great tool? Big YES!
That is actualy great news (expecting that for months). This will stop massive inflow of junk code and poorly written app. So yeah. I am true enemy of classic "vibe coding"
))
i am talking about developer using LLM as agentic enginerring tool to create large scale app, where developer did not write basically any (or just minimu) code by hand, but still have deep understanding about code base, code structure, used patterns, etc.
NGL I’m kinda bummed Fable 5 from Claude was pulled as ordered by the US government. That model was kinda nuts how good it was.
Anyone else play around with local agents? I’ve actually made a beta for a game using local agents and GODOT (a game engine). I’m impressed with what they can do
i only played with gemini so far ( after beeing hint about it by giku in the context of the drambo code module)
i had a brief look at godot (thanks for mentioning it) and it seems to be quite cool.
theres really good learning pages gdquest.github.io. after going through this, i will decide if starting a project will make sense for me. but i'm already 90% convinced:)
Biased, but truly, it depends a lot on what goes into it. I have never avoided disclosing: fourtrack.fm's apps use AI assistance in coding. There's also a LOT of human thought and testing into everything I put out.
Here's the deal with fourtrack.fm and my apps:
If you report a bug and send me an email, you're gonna talk to ME. I'm going to spend hours reproducing it. Yes Claude will help me fix it, but I will verify it manually.
If you have a feature request and want to talk about it, you're going to talk to me and not a bot.
I care deeply that what I work on makes folks happy.
I use AI assistance in coding, but I also have 12 years pro dev experience doing audio hardware development. I hold a doctorate in acoustics.
When I use Claude, I don't just say "vibe me a delay"
I often prototype all my effects and processors in Faust first, which handles the code generation for DSP.
I draw stuff on paper a LOT, and then draw wire frames in Figma.
Then I do some more design research on fonts, colors, doing renders in Blender for stuff like UI elements.
Yes Claude is helping with MCP to Blender, Figma, and writing Swift. It's helping me write C and Rust libraries to do things like sequencers.
I can write harnesses with Claude that make this stuff good. I can do end to end automated tests and quality checks, because I also spent 4 years doing SW test automation for audio applications.
When you spend $5 on something that I poured nights and weekends into, using AI to help, it's not CrapWare or ToolWare or Shovelware.
Fourtrack.fm LOSES money every day that we don't make 3 in app purchases. And most of that after Apple's cut goes straight back into a Claude subscription. As has been stated before, AS OF NOW THERE IS NO MONEY TO BE MADE IN THIS. Would it be hella tight if fourtrack.fm could pay the bills? Sure, but I might have to expand the business well beyond apps for iOS to do this.
I do this because it is awesome and I truly love it. Seriously, this is like the best video game I've ever played. iOS is an incredible canvas for making instruments. I do not want to create landfills of hardware sequencers, effects, and synths. iOS lets me do things that would be wasteful as hardware.
I vibe code. I can’t code. I can read code and I have a need to understand the underlying technology. As far as audio apps go, I don’t think I would try anything truly novel. I use it for the UX layer (currently doing the Airwindows Consolidated auv3 version, beta signup is elsewhere on the site).
What I am good at is design. Almost 30 years experience. Worked with many coders. My angle is that I am careful with the coding and I focus on making UX great.
I have a few working principles to make up for my lack of coding skills:
Everything is open source and on GitHub. Not sure if everything should be free, but skilled coders should be able to inspect everything.
Lots of guardrails against known ai code failures. Everything is heavily documented, code is commented, every part of the internal logic of the app exists in text as well as code, so it doesn’t rewrite huge chunks and change things.
I’m studying the designer approach to agentic ai and in conversation with comp sci / dev friends about that.
I don’t advertise the AI part, but I declare it. I don’t think its mandatory for coders, i think it is for non coders.
So I don’t think I mentioned it on here, but I dont think you can download the beta without seeing that it contains AI generated code.
I worry about AI, and I do not trust it. I think this is essential for working with such a technology,
And I only make things that are needed.
Airwindows Consolidated is an all-admin job. Its not sexy, but its something the community needs. That’s where vibecoders can be useful. Where better coders don’t have time or interest to go.
Btw we need a Vibecoders Anonymous thread on here. Learn from each other and sharpen our skills and principles.
brown and runny!?
I enjoyed reading this thoughtful comment, thank you
That's the vibe on vibe coding? If yes, then I feel like I understand your angle.
This was an excellent post in so many ways.