AI: Who Still Uses Permissions?
Genuinely curious. A year or so ago I grew very tired of having to constantly monitor my terminal in case the agent would ask me for permission to use a tool. I wouldn't have minded that much if the all harnesses didn't suck as much as they do and actually remembered permissions when you tell them to, but they don't, so you end up having to answer "Yes" a quadrigazillion times a day.
So claude has been an alias to `claude --dangerously-skip-permissions`, and codex has had `approvals_reviewer = "auto_review"`, for about a year now.
Anybody else just gave up on coping with broken permission management in their agent?
"Tired" actually doesn't really describe it. It was a level of anxiety closer to a panic attack. Like a constant fight or flight response just looking at the terminal. I feel better now.