Oh surprise, an inexperienced person is doing stupid things and does not even know when to rather stfu, which is a stupid thing only inexperienced people do.

Uhm. “A significant amount of infrastructure”? Uhhhm. Put a reverse proxy in front of your webserver? Problem solved? Or use log analyzers? With alerts?

There is literally no excuse.

It is one thing to use coding agents to produce code. It is another to trust it on reviewing it.

This reminds me of the C compiler written by Claude Code, which was compiling everything, except printf("Hello from CCC!\n");

Hetzner just killed my public IP address because of a random and baseless abuse report. No reaction from their end, just silence. I immediately started migrating to another hoster and deleted my account.

I hope for some large red numbers for Hetzner.

If Arch is this, what is Gentoo? An IKEA car?

Obviously you have no clue how LLM’s work and it is way more complex than just telling it to weite good code. What I was saying is, that even with a very good prompt, it will make up things and you have to double check it. However, for that you need to be able to read and understand code, which is not the case for 98% of the vibe coders.

What people don’t realize is that AI does not write good code unless you tell it to. I am playing a lot with AI doing the writing, while I give it specific prompts, but even then, very often it changes code that was totally unnecessary. And this is the dangerous part.

I believe the only thing repo owners could do is use AI against AI. Let the blind AI contributors drown in work by constantly telling them to improve the code, and by asking critical questions.