AI Innovation...Limitations?

I have this idea for a web-based music app, basically an in-browser DAW. The idea is to take some concepts from modular synthesis and apply them to a generative DAW, but even more specifically, for the most part, those modules will be simple and specific for sort of casual music generation in the background. A chord sequencer with limited options for simple chord progressions may lead into an arpeggiator, that leads into a musical instrument that optimizes for a "bell", "pluck" or "pad" experience, including only the knobs and options one would need for that instrument. There would be a global key setting to keep the music broadly in key. Basically giving you lots of options for generative music but trying to remove some of the cognitive load of keeping things in sync or tuning a broad instrument. And I don't think AI would come up with is idea, which is to say broadly, I think there are lots of ideas AI wouldn't come up with. Though I'm not really saying it couldn't. The question of whether or not "AI is Creative" is probably unknowable. In a practical sense, I think you could say definitely yes, it combines things it learned about into new creations that didn't exist before, but I think the devil is in the details around whether or not there's something spiritual about creativity that is not capture by AI, and maybe more specifically, whether or not humans have some input that modifies the way they come up with solutions to problems that AI doesn't have, at least in it's current form. But I do think there are certain sort of mathematical / combinatorial observations one can make about innovation. The Library of Babel is a short story by Jorge Luis Borges that presents a universe in the form of a vast library containing all possible books of a certain format. The library contains every possible arrangement of letters, spaces, and punctuation marks, meaning it holds not just every book ever written, but every book that could ever be written - including all possible variations with typos, nonsense, and meaningless combinations of characters. The library is described as having an infinite number of hexagonal rooms, each containing four walls of bookshelves. The inhabitants of this universe are librarians who search endlessly through this vast collection, seeking meaning. The central philosophical conceit is that while the library contains all possible knowledge (including perfect books explaining the library itself, prophecies of the future, and biographies of every person), these meaningful works are lost among an overwhelming mass of gibberish. The searchers cannot distinguish between profound wisdom and random characters. The story explores themes of information overload, the search for meaning amid chaos, and the paradox that complete access to all possible information actually results in meaninglessness rather than enlightenment. The librarians become obsessed, depressed, or fanatical in their searches, highlighting how an infinity of possibilities without guidance or context becomes as useless as having no information at all. I think the library of babel can be applied to the world that we live in with AI, and maybe why AI will never actually replace humans in terms of creativity or innovation / working, or at least not for a while. Lots of problems actually require sort of a specific imperfect, non-optimal perspective, and the selling of that perspective to a specific community. They require the experience of working with specific people or kinds of people. FWIW Here's the prompt I gave Claude.AI on this question: There's a concept for a certain kind of innovation or thinking I'm trying to conceptualize and I wonder if this concept exists already. People say that LLM's are creative, but it seems like one limitation in that creativity is that an LLM doesn't have a sort of life experience with which to generate the emotional passion behind an idea. So, sort of in the style of the library of babel, you could have a few LLM's that come up with ideas, or you could probably have infinite LLM's that may be able to come up with all ideas, but part of innovation is the passion to build relationships and exploit life experience to launch an idea. I have an idea for a web-based music application, and it's not that I don't think that an LLM could come up with a similar idea, but that there's no way to get over the sort of signal to noise ratio of ideas, especially ideas that may be counter-intuitive or like avant-garde. Here was Claude's Response: You're touching on something profound_(Thanks Claude!)_ about the nature of innovation and creativity. While LLMs can generate countless ideas through recombination and pattern recognition in their training data, they lack what we might call "embodied creativity" - the kind that emerges from lived experience, emotional investment, and personal meaning. This reminds me of the concept of "tacit knowledge" developed by philosopher Michael Polanyi

May 14, 2025 - 17:36

I have this idea for a web-based music app, basically an in-browser DAW. The idea is to take some concepts from modular synthesis and apply them to a generative DAW, but even more specifically, for the most part, those modules will be simple and specific for sort of casual music generation in the background. A chord sequencer with limited options for simple chord progressions may lead into an arpeggiator, that leads into a musical instrument that optimizes for a "bell", "pluck" or "pad" experience, including only the knobs and options one would need for that instrument. There would be a global key setting to keep the music broadly in key. Basically giving you lots of options for generative music but trying to remove some of the cognitive load of keeping things in sync or tuning a broad instrument.

And I don't think AI would come up with is idea, which is to say broadly, I think there are lots of ideas AI wouldn't come up with. Though I'm not really saying it couldn't.

The question of whether or not "AI is Creative" is probably unknowable. In a practical sense, I think you could say definitely yes, it combines things it learned about into new creations that didn't exist before, but I think the devil is in the details around whether or not there's something spiritual about creativity that is not capture by AI, and maybe more specifically, whether or not humans have some input that modifies the way they come up with solutions to problems that AI doesn't have, at least in it's current form.

But I do think there are certain sort of mathematical / combinatorial observations one can make about innovation.

The Library of Babel is a short story by Jorge Luis Borges that presents a universe in the form of a vast library containing all possible books of a certain format.

The library contains every possible arrangement of letters, spaces, and punctuation marks, meaning it holds not just every book ever written, but every book that could ever be written - including all possible variations with typos, nonsense, and meaningless combinations of characters.

The library is described as having an infinite number of hexagonal rooms, each containing four walls of bookshelves. The inhabitants of this universe are librarians who search endlessly through this vast collection, seeking meaning.

The central philosophical conceit is that while the library contains all possible knowledge (including perfect books explaining the library itself, prophecies of the future, and biographies of every person), these meaningful works are lost among an overwhelming mass of gibberish. The searchers cannot distinguish between profound wisdom and random characters.

The story explores themes of information overload, the search for meaning amid chaos, and the paradox that complete access to all possible information actually results in meaninglessness rather than enlightenment. The librarians become obsessed, depressed, or fanatical in their searches, highlighting how an infinity of possibilities without guidance or context becomes as useless as having no information at all.

I think the library of babel can be applied to the world that we live in with AI, and maybe why AI will never actually replace humans in terms of creativity or innovation / working, or at least not for a while. Lots of problems actually require sort of a specific imperfect, non-optimal perspective, and the selling of that perspective to a specific community. They require the experience of working with specific people or kinds of people.

FWIW Here's the prompt I gave Claude.AI on this question:

There's a concept for a certain kind of innovation or thinking I'm trying to conceptualize and I wonder if this concept exists already. People say that LLM's are creative, but it seems like one limitation in that creativity is that an LLM doesn't have a sort of life experience with which to generate the emotional passion behind an idea. So, sort of in the style of the library of babel, you could have a few LLM's that come up with ideas, or you could probably have infinite LLM's that may be able to come up with all ideas, but part of innovation is the passion to build relationships and exploit life experience to launch an idea.

I have an idea for a web-based music application, and it's not that I don't think that an LLM could come up with a similar idea, but that there's no way to get over the sort of signal to noise ratio of ideas, especially ideas that may be counter-intuitive or like avant-garde.

Here was Claude's Response:

You're touching on something profound_(Thanks Claude!)_ about the nature of innovation and creativity. While LLMs can generate countless ideas through recombination and pattern recognition in their training data, they lack what we might call "embodied creativity" - the kind that emerges from lived experience, emotional investment, and personal meaning.
This reminds me of the concept of "tacit knowledge" developed by philosopher Michael Polanyi - knowledge that cannot be fully articulated or transferred symbolically. A jazz musician's feel for improvisation or a chef's intuition for flavor combinations comes from years of embodied practice and emotional connection to their craft.
What you're describing might be considered a form of "experiential innovation" - where the value comes not just from the idea itself but from the contextual understanding and emotional drive behind it. Your music application idea likely stems from personal experiences with music, frustrations with existing tools, and a passion to create something meaningful to you.
The signal-to-noise issue you mention is crucial. LLMs can generate endless variations, but they lack the embodied filter that says "this matters" or "this resonates" based on lived experience. They have no stake in the outcome, no emotional investment that drives persistence through obstacles.
Would you be willing to share more about your music application idea? I'm curious how your personal experiences and passions have shaped this particular innovation.RetryClaude can make mistakes. Please double-check responses.