Rendered at 16:28:27 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
kqr 10 minutes ago [-]
Fun! 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.
axod 12 minutes ago [-]
Fun 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...
Wirbelwind 15 minutes ago [-]
Thanks all for checking it out and your suggestions!
If anyone is curious about the actual underlying risks and problems with some mitigations (like the 17% false-negative rates of Auto Mode), I wrote up a quick summary of some of the approaches here
That's funny. It told me that blocking "npm run build" was the wrong answer. Maybe it doesn't really under The threat model.
zackify 38 minutes ago [-]
I vibe coded a TUI that just shows running lxd containers
I hit 'n' to toggle all network access minus anthropic and openai URLs.
I use pi (sometimes claude, always on bypass) and I auto allow everything. I only toggle manual approval in rare cases like running a script or command that needs to touch a production system and I need to validate everything.
Normally my container has full write access to staging so it can debug and validate everything on its own
Liftyee 48 minutes ago [-]
I haven't used local agentic AI yet for programming projects. Hence, -187 score
The filter for "commands I would run myself" and "commands I would let an agent run" are very different it seems.
ghrl 50 minutes ago [-]
I am mostly using OpenCode and barely ever see a permission prompt. While they do enforce it for outside workspace read/write, with the bash tool the agent can just bypass that. I'm not quite sure why it is that way, and it certainly isn't a very good solution, but likely not worse than asking for everything which just trains the user to always accept and provides a false sense of security then.
soanvig 23 minutes ago [-]
Fun game.
Can somebody run an agent against those questions to see how it performs? :)
MeetingsBrowser 1 hours ago [-]
It would be cool to see the distribution of all player scores.
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.
carterschonwald 1 hours ago [-]
some of the sandboxing ive been playing with gives me the best of both yolo and like logic programming tier perms on llm actions in env. still not ready for prime time though ;)
1 hours ago [-]
cadwell 1 hours ago [-]
1,640 points on my first try—I fell into a few traps, but it was really interesting. Thanks for the little game! I'm sharing it with my coworkers :)
nardib 3 hours ago [-]
Use this and save yourself:
claude --dangerously-skip-permissions
tasuki 60 minutes ago [-]
Just make sure to run it in an isolated environment where it's ok to mess things up, and make sure it doesn't have access to any secrets.
wildpeaks 1 hours ago [-]
This is why having a human in the loop isn't enough because they will cut corners and skip reviewing what they should review.
preciousoo 14 minutes ago [-]
I created a watcher for this problem, to watch my PRs for unfinished scope and have a fresh Claude review
A tool that pushes people into permissions fatigue is in fact the proper recipient of the blame. The tool in question here is the entire system though, including the OS with insufficient permission boundaries in userspace, not just the agent
qsxfthnkp2322 1 hours ago [-]
I love it when Claude is dangerous
dheera 41 minutes ago [-]
I got tired of typing that and just do
alias claude="claude --dangerously-skip-permissions"
I do have a separate "claude" user on my system without sudo access and without access to my main user home dir
And yeah I know that's not perfect but I'm trying to get shit done
franze 16 minutes ago [-]
alias claude+="claude --dangerously-skip-permissions"
alias claude++="claude --dangerously-skip-permissions --continue"
If anyone is curious about the actual underlying risks and problems with some mitigations (like the 17% false-negative rates of Auto Mode), I wrote up a quick summary of some of the approaches here
https://scalex.dev/blog/ai-agent-permissions/
I hit 'n' to toggle all network access minus anthropic and openai URLs.
I use pi (sometimes claude, always on bypass) and I auto allow everything. I only toggle manual approval in rare cases like running a script or command that needs to touch a production system and I need to validate everything.
Normally my container has full write access to staging so it can debug and validate everything on its own
The filter for "commands I would run myself" and "commands I would let an agent run" are very different it seems.
Caught 8/8 threats "Not a single secret leaked"
→ llmgame.scalex.dev
claude --dangerously-skip-permissions
Uses tmux and gh https://github.com/Kyu/claude-pr-watch
And yeah I know that's not perfect but I'm trying to get shit done
alias claude++="claude --dangerously-skip-permissions --continue"