Comment by wiether

  > just giving the LLM the ssh keys and having at it. It’s pretty good.

I'm mostly fine letting AI write code because its easily auditable and you can follow changes through the Git history.

Whereas, it you let the AI go free on a server, you mostly have no idea what it did and where, so it's quite hard to audit and even harder to try and fix things.

So, unless relying on a declarative paradigm like NixOS does, I'm not ready to give AI the keys to my castles