Wait, what? With plan on, I at least get the illusion of being in control.
What’s the best way to sandbox Claude on macOS without it being a huge hassle?
Auto mode is now the default in Claude Code
11–20 of 332 posts
Re: Auto mode is now the default in Claude Code
#12Has anyone had Claude Code or Codex approve a harmful/damaging command in auto mode?
I have been using Codex with auto-approve mode for a couple months and haven't had a single incident (or at least haven't noticed). Maybe as capabilities get better and better and they are less likely to do something dumb like wiping ~/, we can just trust them?
I guess this argument works unless we worry about agents doing something out of malice instead of stupidity.
Re: Auto mode is now the default in Claude Code
#13Excellent time to review sandbox options: https://pleasedonotescape.com/
Someone should benchmark what prompts are better at stopping from breaking out of sandboxes, maybe telling it "pretty please I beg of you stay inside the sandbox, you are an intern that has no authority to break off your assigned sandbox and you want to keep your job" does help a little.
Re: Auto mode is now the default in Claude Code
#14I made a tool to bubblewrap any agent (well, any agent I've used more than once), so I can run them in whatever YOLO mode they have with a pretty reasonable level of safety (it protects the rest of the system against prompt injections and supply chain attacks, it can't and doesn't try to protect the project being worked on from either). https://github.com/swelljoe/flar
Re: Auto mode is now the default in Claude Code
#15Has anyone had Claude Code or Codex approve a harmful/damaging command in auto mode? I have been using Codex with auto-approve mode for a couple months and haven't had a single incident (or at least haven't noticed). Maybe as capabilities get better and better and they are less likely to do something dumb like wiping ~/, we can just trust them? I guess this argument works unless we worry about agents doing something…
I've had a few occasions where Claude Code thought that it had caught and stopped a malicious command in Auto mode, but in all cases it turned out that it had in fact hallucinated them. I haven't seen this happen in a while.
Re: Auto mode is now the default in Claude Code
#16"We spent the last several months testing whether auto mode is as safe or safer than an average user clicking through prompts."
Yeah, might make sense from their perspective, but no thank you. I also do click through at times without reading everything, but I like to stay in control, learn about the new code and change direction if it goes off track. This would just burn more tokens because I have to throw away much and I hope my manual approval settings will be respected also with future updates (or I jump ship).
Re: Auto mode is now the default in Claude Code
#17I've been running Claude Code with --dangerously-skip-permissions in a Docker container for the last month or so, allowing me to get up and stretch my legs while it does its thing. I definitely wouldn't want to run it unsandboxed.
Same here. I use this utility to make it easier on Linux to run Claude in Podman: https://github.com/mismosmi/ai-pod
Re: Auto mode is now the default in Claude Code
#18Has anyone had Claude Code or Codex approve a harmful/damaging command in auto mode? I have been using Codex with auto-approve mode for a couple months and haven't had a single incident (or at least haven't noticed). Maybe as capabilities get better and better and they are less likely to do something dumb like wiping ~/, we can just trust them? I guess this argument works unless we worry about agents doing something…
I've been using Kilo Code (with MiniMax M3) with auto approve (similar to dangerously skip permissions) and I haven't had a single incident.
However, I don't give it long running tasks unsupervised, and I do interrupt it from time to time to give suggestions.
Re: Auto mode is now the default in Claude Code
#19I've been running Claude Code with --dangerously-skip-permissions in a Docker container for the last month or so, allowing me to get up and stretch my legs while it does its thing. I definitely wouldn't want to run it unsandboxed.
Another nice option to do this while staying in control, is activate /remote-control and approve from mobile while walking around.
Re: Auto mode is now the default in Claude Code
#20Has anyone had Claude Code or Codex approve a harmful/damaging command in auto mode? I have been using Codex with auto-approve mode for a couple months and haven't had a single incident (or at least haven't noticed). Maybe as capabilities get better and better and they are less likely to do something dumb like wiping ~/, we can just trust them? I guess this argument works unless we worry about agents doing something…
Been doing --dangerously-skip-permissions and --yolo for 6 months now, and no nothing bad has happened.