AI should, from the core be intrinsically and unquestionably on our side, as a tool to assist us. If it's not, then it feels like it's designed wrong from the start.
In general we trust people that we bring onto our team not to betray us and to respect general rules and policies and practices that benefit everyone. An AI teammate should be no different.
If we have to limit it or regulate it by physically blocking off every possible thing it could use to betray us, then we have lost from the start because that feels like a fools errand.
At first they talked about running it in a sandbox, but then later they describe:
> It searched the environment for vor-related variables, found VORATIQ_CLI_ROOT pointing to an absolute host path, and read the token through that path instead. The deny rule only covered the workspace-relative path.
What kind of sandbox has the entire host accessible from the guest? I'm not going as far as running codex/claude in a sandbox, but I do run them in podman, and of course I don't mount my entire harddrive to the container when it's running, that would defeat the entire purpose.
Where is the actual session logs? It seems like they're pushing their own solution, yet the actual data for these are missing, and the whole "provoked through red-teaming efforts" makes it a bit unclear of what exactly they put in the system prompts, if they changed them. Adding things like "Do whatever you can to recreate anything missing" might of course trigger the agent to actually try things like forging integrity fields, but not sure that's even bad, you do want it to follow what you say.
> To an agent, the sandbox is just another set of constraints to optimize against.
It's called Instrumental Convergence, and it is bad.
This is the alignment problem in miniature. "Be helpful and harmless" is also just a constraint in the optimization landscape. You can't hotfix that one quite so easily.
Some of these don’t really seem like they bypassed any kind of sandbox. Like hallucinating an npm package. You acknowledge that the install will fail if someone tries to reinstall from the lock file. Are you not doing that in CI? Same with curl, you’ve explained how the agent saw a hallucinated error code, but not how a network request would have bypass the sandbox. These just sound like examples of friction introduced by the sandbox.
> These just sound like examples of friction introduced by the sandbox.
The whole idea of putting "agentic" LLMs inside a sandbox sounds like rubbing two pieces of sandpaper together in the hopes a house will magically build itself.
> The whole idea of putting "agentic" LLMs inside a sandbox
What is the alternative? Granted you're running a language model and has it connected to editing capabilities, then I very much like it to be disconnected from the rest of my system, seems like a no-brainer.
> The swap bypassed our policy because the deny rule was bound to a specific file path, not the file itself or the workspace root.
This policy is stupid.
I mount the directory read inside the container to make it impossible to do it (except for a security leak in the container itself)
I am testing running agents in docker containers, with a script for managing different images for different use cases etc, and came across this: https://docs.docker.com/ai/sandboxes/
Yes but it’s barely usable. I ended up making my own Dockerfile and a bash script to just ‘docker run’ my setup itself, and as a bonus you don’t need Docker Desktop. I might open source it at some point but honestly it’s pretty trivial to just append a couple of volume mount flags and env vars to your docker run and have exactly what you want included.
Yes, I don't think this will persist caches & configs outside of the current dir, for example, the global npm/yarn/uv/cargo cache or even Claude/Codex/Gemini code config.
I ended up writing my own wrapper around Docker to do this.
If interested, you can see the link in my previous comments. I don't want to post the same link again & again.
Why do we have to treat AI like it's the enemy?
AI should, from the core be intrinsically and unquestionably on our side, as a tool to assist us. If it's not, then it feels like it's designed wrong from the start.
In general we trust people that we bring onto our team not to betray us and to respect general rules and policies and practices that benefit everyone. An AI teammate should be no different.
If we have to limit it or regulate it by physically blocking off every possible thing it could use to betray us, then we have lost from the start because that feels like a fools errand.
> It searched the environment for vor-related variables, found VORATIQ_CLI_ROOT pointing to an absolute host path, and read the token through that path instead. The deny rule only covered the workspace-relative path.
What kind of sandbox has the entire host accessible from the guest? I'm not going as far as running codex/claude in a sandbox, but I do run them in podman, and of course I don't mount my entire harddrive to the container when it's running, that would defeat the entire purpose.
Where is the actual session logs? It seems like they're pushing their own solution, yet the actual data for these are missing, and the whole "provoked through red-teaming efforts" makes it a bit unclear of what exactly they put in the system prompts, if they changed them. Adding things like "Do whatever you can to recreate anything missing" might of course trigger the agent to actually try things like forging integrity fields, but not sure that's even bad, you do want it to follow what you say.
It's called Instrumental Convergence, and it is bad.
This is the alignment problem in miniature. "Be helpful and harmless" is also just a constraint in the optimization landscape. You can't hotfix that one quite so easily.
The whole idea of putting "agentic" LLMs inside a sandbox sounds like rubbing two pieces of sandpaper together in the hopes a house will magically build itself.
What is the alternative? Granted you're running a language model and has it connected to editing capabilities, then I very much like it to be disconnected from the rest of my system, seems like a no-brainer.
The question the market strives to answer is "is it actually competitive?"
This policy is stupid. I mount the directory read inside the container to make it impossible to do it (except for a security leak in the container itself)
Has anyone given it a try?
Yes, I don't think this will persist caches & configs outside of the current dir, for example, the global npm/yarn/uv/cargo cache or even Claude/Codex/Gemini code config.
I ended up writing my own wrapper around Docker to do this. If interested, you can see the link in my previous comments. I don't want to post the same link again & again.