Diagnosed with ADHD, ultimately does not change anything for me even through i had the same idea as you. Reason is that i can now start even more stuff in parallel. And some part of them get finished more before i can just prompt more when in focus, but instead of finishing i add more features.

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.

I am the same. Most my projects were infra leaning and I had a very general idea of what I wanted, not clear steps. I learned a ton in the process of cleaning up my home networking, understood network topology and restrictions, how to work around ISP imposed bullshit and setup a home network accessible remotely and securely. I also learned about stacks like Portainer/Adguard etc. Setting up Raspberry pi as a general purpose server including media serving via Jellyfin. Until you do it, even with the LLM doing the heavy lifting, you won't learn how to work around the issues.

I setup exactly one personal finance service/dashboard and one Android app for a specific purpose. Then I stopped because my needs were met. I'm sure I will get into it when I need to again.

You can either use it as a PoC testing enabler in which case it will be bunch of unfinished things. Or you can be deliberate and focused about your goals and the results will match that. Of course being a software developer helps.

I feel the same. I not sure if I have ADHD, but I always have 2 mode of focusing on something, first one is shot burst of focus and other one is real locked in mode where I forgot to eat or drink water. While second one is much better at delivering value it mostly activated on management/strategy games that I love :D But with AI assisted coding now I can really work on my side project while having first focus mode. Im just writing or designing the parts I excited about, and then I let AI to handle boring task.

Honestly it’s been amazing for me for similar reasons. Also diagnosed ADHD.

Starting projects has always been easy. But once I figured out the hard stuff and then had everything figured out and only saw the long road ahead of drudgery and pipe laying my motivation fizzles out unless my paycheck depends on it.

Now? I still get to figure out the fun hard part and then go send a cheap fast working dumb minion to do the tedium.

I’ve finished 3 things in the past month that have been on my hobby list for years with no progress. It’s been really freeing.

The real moment of truth will be if it’s still worth the cost for tasks that have human value and users but aren’t profitable, which is where most of my side projects live. At current rates it is for me, but once the VC subsidies evaporate then maybe not.