Yes. That seems to be the case.
While it may not be saving any time compared to generating general python code vs. specific symbolic code, the real value could be that it has an engine to enforce the contract on LLM responses with the library or even do the calls to the LLM as a common piece of code making it less error prone and bringing consistency in the interactions with the LLM.
Since code is generated by LLM these days, how does specific syntactic constructs like a Symbol which essentially carries the context and can be manipulated with python operators help when compared to a normal python code generated by LLM with all the checks and balances instructed by a human?
For example, I can write in this syntax to convert all fruits to vegetables or I can simply prompt an LLM to construct a program that takes a list of fruits and calls a LLM in the background to return the vegetables equivalent.
I am trying to understand the difference.
The problem with organizing is not the lack of tools or techniques.
It is simply not possible to devise a system which works automatically with little effort.
Everything requires varying levels of discipline which is hard to keep up with time and a different situation.
Humans seem to do a million different things. And all of them were kids growing into adults and do by learning to do things.
Isn't that good enough if a machine did just that - ready to learn if taught, to be classified as being generally intelligent ?
I've been a dev building things and I can resonate with what you say very much.
A builder is like someone who has a hammer in his hand with everything around looking like a nail.
Esp. if you are a builder who is constantly excited with your own ideas, it's hard to ask who would want that ?