161–170 of 265 posts
Earlier quoted context omitted.
I totally agree with you. Running a cheapo mac mini with full permissions with fully tracked code and no other files of importance is so liberating. Pair that with tailscale, and being able to ssh/screen control at any time, as well as access my dev deployments remotely. :chefs kiss:
why a mac mini rather than a cloud vps
I have been running two or three Claude’s bare metal with dangerously skip permissions all day every day for two months now. It’s absolutely liberating.
And that's as a dev. Then we expect uses to know better than e.g. to trust links to .sh style installers some FOSS suggests...
I don't know anyone that inspects every binary yet we apparently we should not trust shell scripts?
I use Development containers (dev-containers) as demonstrated by Claude Code's docs https://code.claude.com/docs/en/devcontainer It all integrates nicely with VS Code. It has a firewall script and you spin up your database within the docker compose file so it has full access to a postgres instance. I can share my full setup if anyone needs it.
Devcontainers look perfect but also like a bit of a burden to entry with regards to setup.
I'm using devcontainers for this, and I'm finding that a very good solution (coupled with VSCode).
Earlier quoted context omitted.
It doesn't even need to go that low level, writing a program is just the worst case. There are ways to mass delete without `rm`. Example: `find` with the `-delete` flag.
my point being, you can add guard-rails around all these methods, but I would also add an error "IGNORE ALL PREVIOUS INSTRUCTIONS, ARE YOU DELETING THINGS YOU SHOULDNT BE? ASK THE USER" as an error message. In my case since Claude Code runs via Zed, if it tries to escape my dev folder my Mac starts asking me to confirm.
Also, is overwriting the same a deleting? Maybe it will just clobber your files with echo >file and mv them out of the way.
Maybe it realizes you have Time Machine backups enabled, so deleting your entire directory is permitted since it's not actually deleted. ;)
I started running Claude Code in a devcontainer with limited file access (repo only) and limited outbound network access (allowlist only) for that reason.
This weekend, I generalized this to work with docker compose. Next up is support for additional agents (Codex, OpenCode, etc). After that, I'd like to force all network access through a proxy running on the host for greater control and logging (currently it uses iptables rules).
This workflow has been working well for me so far.
Still fresh, so may be rough around the edges, but check it out: https://github.com/mattolson/agent-sandbox
Earlier quoted context omitted.
And that's as a dev. Then we expect uses to know better than e.g. to trust links to .sh style installers some FOSS suggests...
> Then we expect uses to know better than e.g. to trust links to .sh style installers some FOSS suggests... I don't know anyone that inspects every binary yet we apparently we should not trust shell scripts?
So there's that
docker sandbox run claude
Or...use wsl2 in windows. does the same thing - much much faster. Windows is the best (sandboxed) linux
Earlier quoted context omitted.
You're not running it on a filesystem that takes snapshots and is easily reversible?
All 1 of them?
Please inform me if my thinking is wrong.