I have been doing something similar. In my case, I prefer reading reference documentation (more to the point, more accurate), but I can never figure out where to start. These LLMs allow me to dive in and direct my own learning, by guiding my readings of that documentation (i.e. the authoritative source).
I think there has been too much emphasis (from both the hypesters and doomsayers) on AI doing the work, rather than looking at how we can use it as a learning tool.
Claude Code gives me a directory, usually something that works, and then I research the heck out of it. In that way I am more of an editor, which seems to be my stronger skill.
You are an inspiration. I will remember this when I grow older. Just wanted to say this, I am 1/2 your age, and I am sure there are 1/3 or even 1/4 people here. ;)
I personally think coders get better with age, like lounge singers.
Learning for what? That day when you write it yourself, that will never come ...
There is only so much you can learn by reading; it requires doing.
The good thing about traditional sources like books, tutorials and other people's code bases is that they give you something, but don't write your project for you.
Now you can be making a project, yet be indefinitely procrastinating the learn-by-doing part.
For the enjoyment, and producing better products, faster?
Why were you learning, before AI tools?