Comment by letmetweakit
1 day ago
I run Claude in a Proxmox VM, generally the experience has been great. In my experience it also behaves better than gemini cli, that likes to create files all over the place if set loose (lesson learned to add that requirement to the relevant .md files)
Something that contains Claude even more in this respect is if you explicitly gives it a directory that you tell it is entirely under its control, and tells it to write md files and other intermediate work products there (and this seems to work better than telling it where it isn't allowed to leave things).
That sounds like a good idea. When I have a one-off need for misc files I tell it to put them in the project’s ./tmp because that’s already in my global gitignore. That generally works, but I still run into surprise files it leaves in source dirs like a puppy leaves turds on a rug. I’ll try adding that to my instructions instead of doing it one-off.
I've often found that LLMs don't listen to "Don't do" commands with anywhere near the same gusto as "Do" commands.
People don't usually think about pink elephants, unless you ask them not to think about pink elephants :)
I too use this solution, using both Ubunutu LXCs and full-fledged VMs. Only issue I've struggled with has been losing SSH connection on the LXC, and tmux and session both seem to mess up the terminal formatting in CC.
I do agree with the security / cautionary comments and wouldn't leverage this setup outside a hacked together homelab.
This was also the direction I was initially headed, but then I realized I wanted one-VM-per-project so it can really do anything it wants on the complete VM. So the blast-from-the-past-Vagrant won because of the Vagrantfile + `vagrant up` easiness.
I use Proxmox snapshots to get back to a clean state. I’ll take a look at Vagrant too though.
In installed Gemini as an extension in VS Code and it kept wanting to index all my files. Still trying to figure out what it was doing outside of the VS Code folder I had set it to work on.