Edge AI11 min read
Voice AI for Multilingual Yacht Crews
Build, buy, or self-host voice assistants for multilingual yacht crews. Real latency numbers for Whisper, Piper, and Deepgram on vessel hardware.
Ethan Marsh·May 24, 2026
Long-form
Field Notes
Dispatches from the bridge on sovereign AI at sea, infrastructure, security, edge models, and the operational engineering of systems that keep working when the link drops. For news and commentary, visit The Watch.
Infrastructure12 min read
Vessel GPU Racks: Power, Cooling, Security
The unglamorous realities of deploying GPU compute on a vessel. Power budgets, thermal management, vibration isolation, and physical access control.
James Calder·May 17, 2026
Security & Compliance11 min read
Zero-Trust Networks for Private Vessels
Most vessel networks were designed for convenience, not security. A practical zero-trust architecture for superyacht IT and OT segmentation.
Marcus Hale·May 10, 2026
Edge AI11 min read
Agentic Workflows for Yacht Concierge
How to architect a multi-tool AI concierge that handles guest requests on a charter yacht, with or without a satellite link.
Ethan Marsh·May 3, 2026
Networking10 min read
Starlink, OneWeb, Iridium for AI at Sea
A working comparison of Starlink Maritime, Eutelsat OneWeb, and Iridium Certus for vessel AI workloads. What each is good for, and what breaks at sea.
James Calder·April 26, 2026
Edge AI12 min read
Deploying a 70B LLM Offline at Sea
Hardware, quantization, and serving stack for running Llama 3.1 70B on a vessel with no cloud fallback. Real specs and real benchmarks.
Ethan Marsh·April 19, 2026
Security & Compliance13 min read
CMMC Compliance for Superyachts
Most superyachts are not DoD contractors, but CMMC and NIST 800-171 still matter. The compliance map: what applies and what to build.
Marcus Hale·April 12, 2026
Infrastructure18 min read
On-Vessel GPU Selection Guide
Blackwell B200, H200, H100, L40S, and A100 compared for vessel deployments. When each is the right call and the power realities.
James Calder·April 11, 2026
Infrastructure15 min read
Unified Memory for Vessel AI
AMD Strix Halo and NVIDIA DGX Spark bring 128 GB of unified memory to a shelf-sized box for under $4,000. When to buy one.
James Calder·April 10, 2026
Networking6 min read
Satellite Internet: The Real Story
Starlink promised 200 Mbps. You are getting 11. What satellite connectivity actually looks like on a vessel and how to plan for it.
James Calder·April 9, 2026
Edge AI6 min read
AI Concierge That Works Mid-Ocean
Cloud chatbots fail when the ship leaves port. Here is what an on-vessel AI concierge looks like, and why guests will not notice.
James Calder·April 1, 2026
Resilience6 min read
Crew Management Without the Cloud
On-vessel AI handles crew scheduling, certifications, and compliance for 2,000+ crew without relying on a satellite link.
James Calder·March 25, 2026
Resilience6 min read
Engine Monitoring at Sea: A Hard AI Problem
Cloud-based predictive maintenance breaks down at sea. Here is why catching engine trouble mid-ocean is a harder AI problem than it looks from shore.
James Calder·March 18, 2026
Edge AI6 min read
Why Vessel Safety CV Has to Run Locally
Man overboard detection and deck safety monitoring are latency-sensitive problems. Here is why shore-side processing cannot meet the operational bar.
James Calder·March 11, 2026
Resilience5 min read
Why Cloud AI Fails at Sea
Your satellite link cannot support cloud-based AI on a vessel. Here is why, and what actually works 200 miles from shore.
James Calder·March 4, 2026