I guess I'm between you and OP.

I've definitely spent too many sprints where LLMs told me that something would be easy and they could definitely do it, and then... 2 days later I'm still debugging their crap before it dawns on me... WTF am I doing with my time?!

Overall, I've built a memory safe programming language that solves a lot of problems I personally have - predominately in my spare time over 8 months - and I've learned A TON in the process.

I'm close to a release stage, and on top of that - I've built a lot of good tooling for Ruby that I think other people will find helpful once I polish it (especially if anyone plans to vibe code something non-trivial in Ruby - which I honestly wouldn't recommend).

But... I'm not really sure this is what I actually wanted to do with my time, and I'm constantly questioning how much time I'm sinking into this and why...

It started off as utter amazement of what LLMs can do, and then incredible frustration at what they can't do, and my unending desire to figure out why they're so bad at things so close to what they are exceptionally good at, and if there's anything I can do to bridge that gap.

That's partially what the language is designed for (before I even started using LLMs).

But after all this time... I'm not even sure I've really figured anything out tbh.