431–440 of 440 posts
Can a user blindly trust this sandbox, because that's how people will treat it based on the marketing. Sounds like it could be useful for far more than just AI though.
Earlier quoted context omitted.
“microvms” are real vms but the hypervisor and vm (guest kernel) shed most of the hardware / device emulation, support, and discovery which makes traditional VMs look / feel like real computers, as well as most guest interactions. This gives them extremely low overhead. Firecracker is designed to start a VM in under 125ms and 5MB. Netbsd advertises that you can direct-boot a MICROVM kernel configuration in under 10ms…
If an agent fires up NPM, takes a boatload of memory, is that memory released back to the OS after NPM shuts down in the VM?
I think this is one of the big issues with today's MCP servers. Most are based on Node.js and take a lot more memory than they should, compared to the complexity that the job requires. Just run a few MCP servers locally, and all your RAM is gone...
Earlier quoted context omitted.
Yes, I've worked with people who have run into issues with "security" solutions like ZScaler. I have tried it with some APIs (like GitHub) and it does work. Not to say it will work in your case.
I was just interested how it works, because above it was sold as “it works”, when in reality, “it works*”.
Earlier quoted context omitted.
Windows Hypervisor Platform, to my understanding. https://learn.microsoft.com/en-us/virtualization/api/hypervi... https://www.qemu.org/docs/master/system/whpx.html
Fun fact: QEMU runs natively on windows and supports acceleration with WHP. It works surprisingly well.
On Windows 11, too? At least for hardware virtualization in VMWare one would have to disable Windows Device Guard & Credential Guard for that.
So what "sandboxing" does this add that is not already present in Docker, and how can users be any more assured that software cannot break out (which has happened at times with Docker). Can a user blindly trust this sandbox, because that's how people will treat it based on the marketing. Sounds like it could be useful for far more than just AI though.
Docker Sandbox spawns a micro VM, not a standard container isolated by host kernel mechanisms (Linux namespaces etc.)
Does this support Linux yet? When I previously looked it did not (the reason being that they were already using VMs on Windows/macOS but not on Linux). Every time I see an announcement I think "great, they must've added Linux now then", but the linked pages always have Windows + macOS instructions but not Linux. All the open GH issues about supporting Linux that I subscribed to have gone unresponded to. OpenShell loo…
It must be a joke that this tool is not supported on linux yet, although docker is built on top of linux containers. Shame on docker.
https://docs.docker.com/ai/sandboxes/#get-started has instructions for Ubuntu.
Does this support Linux yet? When I previously looked it did not (the reason being that they were already using VMs on Windows/macOS but not on Linux). Every time I see an announcement I think "great, they must've added Linux now then", but the linked pages always have Windows + macOS instructions but not Linux. All the open GH issues about supporting Linux that I subscribed to have gone unresponded to. OpenShell loo…
I think Linux has a better solution than Docker. I wrote a tool to use `bubblewrap` to containerize any agent (at least all the agents I've used a couple of times), and bind mount the system stuff read-only, so the agent has your "usual" environment, but they can only see the project. Their history persists (either through a bind mount or a "shadow" copy of the history that only the wrapped agent sees), the agent can…
Open source alternative with podman support and local telemetry collection https://github.com/VibePod/vibepod-cli
Before you use no sandbox at all use this or one the many similar projects but it's alway worth remembering that Docker is not a security boundary. It never has been meant to be and never will become one. cgroups are a mechanism designed for hierarchical organization and resource distribution. Against a malicious and capable actor, and that is how we have to treat AI agents, cgroups will not withstand. Also, the kern…
I do not see any value proposition in this - if I need a sandbox, I make one with Dockerfile, Bubblewrap or virtualization. What I am missing? An enforced required login is a net negative value - it means rug pulls in the future.