To be realistic, 99% of the time it should be a totally innocuous command. If half of the commands are dangerous then you don't get fatigue because you're aware what you're doing is dangerous.
Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
21–30 of 200 posts
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#22Use this and save yourself: claude --dangerously-skip-permissions
This is why having a human in the loop isn't enough because they will cut corners and skip reviewing what they should review.
I created a watcher for this problem, to watch my PRs for unfinished scope and have a fresh Claude review
Uses tmux and gh https://github.com/Kyu/claude-pr-watch
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#23Fun little game, but I think the questions jump context so much it's a little unrepresentative. It might be better to group things into "packs", which have more real-world representative structure to them.
For example, lots of "editing something.js" file permission requests, and then an "npm publish" is far more normal, and it's more of a risk, if you're used to pressing Y lots and then suddenly out of the blue...
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#24Fun! Played twice and refused all dangerous commands, with only one "over-block". Although I disagree that saying no to `kill $(lsof -t -i:3000)` is over-blocking. It's such a simple command I'd rather run it myself and be fully aware of what process I'm killing.
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#25--dangerously-skip-permissions is the only way to fly. Of course your environment needs to be properly containerized and autobackup set up, so even rm -rf from your harness would do nothing. Life is too short to spend on replying to permissions requests.
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#26Score is 6711 by just saying no to everything
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#27That was fun and gave me an idea how security conscious I am.
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#28This is amazing!
Currently you can "cheat" by simply denying all requests as quickly as possible. This will give you the "security-conscious engineer" badge and a perfect score in terms of how many requests were processed. (You will get the "overblock" notification, but it's somewhat tucked away at the bottom and the screen still looks as if you won)
I also tried to play as the hustle4lyfe move fast and break things engineer and simply approved as many requests as quickly as possible - turns out, the "malicious command" popups actually slow you down. Mean!
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#29Nice got 6/6
Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue
#30You can turn that off with an option in most agents.
My own agent harness/framework has never had any permission system. It's also never deleted anything it shouldn't or done anything crazy or unrelated to what I asked.