Knowledge base

Security and privacy: what we do, and what we don't

Where prompts go, what a host can and cannot see, how artifacts are pinned and verified, and an honest account of what sandboxing is in place today.

Distributed inference raises two fair questions: what happens to a customer's prompt, and what happens to a host's machine. Here is the current answer to both, including the parts that are still work in progress.

If you send us prompts

If you host

What is not done yet

The engine today runs as an unprivileged child process, not inside a sandbox with a syscall filter. Hardening that — seccomp and Landlock on Linux, no-egress containers for the vLLM tier — is scheduled, and we would rather say so plainly than imply a boundary that isn't there yet. The technical specification describes both the current state and the target.

Verify rather than trust

mahout is open source and its releases are checksummed. You can read what it does before you run it, and check that what you downloaded is what we published.

See also: the model catalogue · download mahout · how the whole system works · the blog