I've vibe coded an application to see what it's like (rz01.org)

I did that too[1], twice[2] :-).

[1] https://seaquel.app

[2] https://github.com/webstonehq/tuxedo

Nice take.

"...I can’t really call “vibe coding”. I didn’t code. I didn’t even look at the code"

I thought that was the definition of vibe coding?

   - As a professional developer, I would find it very frustrating to have to debug someone else's code and also be held responsible for that code.
   
   - As a hobbyist developer, it would bother me that I'm no longer a developer.

These two statements articulate my feelings about LLM-generated code better than I have heretofore been able to do myself.

a bit off-topic, and you've probably already tried this, but if you want a really nerdy way to log qso, try FLE in a text editor:

https://github.com/on4kjm/FLEcli

Ive downloaded a coding harness and using local llm to improve self hosting and security.

Seems fairly easy but whereas hand coding i run into bugs that are some dark corner of the code,now i do the same but cant do more than yell at the LLM to do better.

Im still saving time but the different types of bugs are fascinating.

You should look at the code. It sucks. It will make you feel sick. It does the thing but you are right - you won’t want to maintain it. It makes you feel hollow inside like when you are coming down from acid

> I can code in Python myself. Not particularly well, but I can get done what I want or need to get done. What happened today, I can’t really call “vibe coding”. I didn’t code. I didn’t even look at the code. My role was that of a client or project manager who contracted someone/thing else to code for money. Furthermore, I was also the QA guy testing the application and giving feedback to Claude.

We did a hackathon at work recently, and this was definitely one thing I learned during the process of our team using Claude to do the whole thing. (Using Claude was an explicit stated goal of the hackathon, fwiw; every team did this.)

It felt very strange.