Here're some useful insights from playing with Muse Code over the last few days, especially around permissions and safet...

Here're some useful insights from playing with Muse Code over the last few days, especially around permissions and safety.Muse Code gives us two independent layers of control:- Approval layer: decides when Muse must pause and ask.- Sandbox layer: enforces filesystem and network boundaries.Examples with the sandbox enabled:๐Ÿ”’ Strictmuse --approval-mode untrusted --sandbox-network restrictedโš–๏ธ Balanced/defaultmuse --approval-mode on-request --sandbox-network proxy-only๐Ÿš€ Autonomous but containedmuse --approval-mode never --sandbox-network enabledNetwork options:- restricted โ†’ no network access- proxy-only โ†’ approves connections per destination- enabled โ†’ full network accessTo lower or remove guardrails:- muse --disable-approval โ†’ no approval prompts; sandbox stays on- muse --disable-sandbox โ†’ approvals stay on; sandbox and workspace confinement are removed- muse --yolo โ†’ disables both layers and trusts the workspace#meta #ai #musecode

Read Original

Related