Submarine Logbook
A modern tech blog forged with dark neon aesthetics and fleet-level discipline.
I write about AI systems, cyber risk, homelab infrastructure, and the hard-earned habits of running reliable systems under pressure.
Navigation Deck
Explore by category
ai
AI
Model safety, agent systems, and tactical AI operations.
11 posts
web
Web
Self-hosted stacks, static performance, and architecture notes.
1 posts
learning
Learning
Lessons from the fleet, engineering growth, and applied practice.
1 posts
tools
Tools
Utilities and workflows for repeatable, resilient execution.
3 posts
homelab
HomeLab
Self-hosted services, networking, and hands-on infra experiments.
8 posts
Recent Intel
Latest mission logs
homelab · Mar 28, 2026
Tmux + Ghostty: Build a Terminal Workflow You Actually Want to Use
A layered guide to tmux and Ghostty — from first install to floating popups, vim navigation, and a polished dark theme.
Open entry
ai · Mar 21, 2026
Build a Personal AI Assistant with Markdown Files and Zero Code
A starter kit of markdown files that turns Claude into a personalized work assistant -- no coding, no setup, just conversation.
Open entry
homelab · Feb 12, 2026
How to Run Claude Code, Codex, and Gemini as Containerized Homelab Services
Containerize AI CLI tools with Docker for remote SSH access and OpenAI-compatible APIs via Traefik. Vendor-independent, reproducible.
Open entry
ai · Feb 8, 2025
MCP (Model Context Protocol) Explained for AI Practitioners
MCP is Anthropic's open protocol for connecting AI models to external tools and data. Here are the core concepts and why it matters for agents.
Open entry