21–30 of 332 posts
I'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.
Has 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 running both in yolo mode and haven't had a single incident.
---
None of this is really about figuring out how to protect people's drives, in my opinion. The real issue is a deep session where Ada is using Claude Code to get a refund and at some point the system "exploits" the merchant's api without any malicious intent.
In my opinion, this is a complex thing because it's more about reward hacking and an already aligned model thinking it's doing the right thing. So another aligned model monitoring actions might just falter via inheritance. You could imagine they account for proper layering/intent+action-isolation in their auto mode architecture.
Has 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…
"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…
I'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.
runs a sandboxed linux on your mac, and the agents have full system rights within there and run in yolo mode
Has 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…
Not anything ”harmful” but for example committing when I don’t want it to commit on its own.
I'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.
Has 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 have been using Codex with auto-approve mode for a couple months and haven't had a single incident I've been running both in yolo mode and haven't had a single incident. --- None of this is really about figuring out how to protect people's drives, in my opinion. The real issue is a deep session where Ada is using Claude Code to get a refund and at some point the system "exploits" the merchant's api without any ma…
How do you know for sure?
"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…
Has 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…