PC Watch's Liu Yao: Using Tailscale+SSH to Free Meta Muse from Cloud VMs for Autonomous Programming on a 21-Year-Old Zaurus and a 7-Year-Old Jetson Nano
PC Watch author Liu Yao found that the cloud virtual machine environment of Meta Muse (4-core EPYC + 8GB RAM) limited its coding capabilities. He bridged Muse to local PCs and legacy hardware via Tailscale and SSH, enabling an autonomous development verification loop. Muse completed a Zaurus megademo in 30 minutes and ported llama.cpp to a Jetson Nano after 17 patches to run a 230M parameter LLM, but performance (419.6 tok/s prefill) remained significantly behind Claude Code's optimized results (656.2 tok/s). The author attributes this gap to workflow differences: Claude Code probes behavior first, while Muse guesses and advances quickly.
Meta's AI agent Muse runs on a cloud virtual machine with a 4-core EPYC processor and 8GB of memory. This configuration is more than sufficient for daily tasks such as managing emails, scheduling appointments, and setting timed reminders. However, if you want it to write code, compile programs, and verify them on real devices, this virtual machine becomes a cage: it cannot access physical hardware, cannot run tests independently, and must hand over its outputs to humans for verification before receiving feedback.
In November 2026, PC Watch author Liu Yao published a detailed practical record demonstrating a method to bypass this limitation: establishing an encrypted tunnel via Tailscale so that Muse's cloud VM can remotely operate a local PC via SSH, which then serves as a bridge to connect to deeper legacy hardware. The entire chain is structured as follows: Muse VM → Tailscale+SSH → MINISFORUM MS-R1 (12-core ARM, 64GB RAM, Tesla P4 GPU) → Telnet → Sharp Zaurus SL-C1000 (a 2005 Linux PDA with 64MB RAM).
The core value of this bridging lies in granting the AI self-verification capabilities. Within the virtual machine, Muse could only write code, compile install packages, and hand them to humans for execution on physical devices. Once it could directly operate the target device, it could complete the closed loop of 'write → compile → run → screenshot → check → correct' on its own. Liu Yao had Muse develop a megademo on the Zaurus, which launched within 30 minutes—a speed previously unattainable through human verification feedback loops. However, the loop was not perfect: Muse captured images from the frame buffer but did not truly 'see' the screen, resulting in upside-down visuals. After being informed, it flipped the image left-to-right instead. Ultimately, the author had to take a photo of the physical screen and send it to Muse to correct the orientation issue.