SubDepthTech publisher mark SubDepthTech Deep systems / precise control
Dispatch
Menu

Archive / Logbook

The full archive

Every published SubDepthTech dispatch lives here, grouped by year and cross-indexed by topic. Search stays in the masthead so the archive can stay readable.

2026 4 entries
Lab

Mar 28, 2026 12 min read

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.

  • #tmux
  • #ghostty
  • #terminal
Systems

Mar 21, 2026 25 min read

AI Will Not Take Your Job, But It Might Take Your Ability to Think

The real AI risks are not about capability. They are critical thinking erosion, organizational inertia, and a misunderstanding of both AI and security.

  • #ai-agents
  • #claude-code
  • #codex
Systems

Mar 21, 2026 7 min read

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.

  • #claude
  • #ai-assistant
  • #starter-kit
Lab

Feb 12, 2026 10 min read

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.

  • #claude-code
  • #codex
  • #gemini
2025 21 entries
Systems

Nov 22, 2025 14 min read

I Monitored a Chinese AI Model for Bias. Here's What I Found.

GLM 4.6 monitoring revealed 12% geographic bias, narrative injection, and trust-building patterns. Empirical security research on lower-cost AI model behavior.

  • #ai-security
  • #bias-detection
  • #research
Systems

Nov 21, 2025 15 min read

Prompt Injection: The SQL Injection of AI (But Unsolvable)

Prompt injection is the defining LLM vulnerability with no parameterized query fix. Unlike SQL injection, it may be theoretically impossible to solve.

  • #ai-security
  • #prompt-injection
  • #vulnerabilities
Systems

Nov 20, 2025 12 min read

Why AI Security Broke Traditional InfoSec Playbooks

Traditional CISSP frameworks fail against prompt injection and unsolvable AI vulnerabilities. Here's why agility matters more than stability in AI security.

  • #ai-security
  • #infosec
  • #cissp
Systems

Feb 8, 2025 8 min read

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.

  • #mcp
  • #ai-agents
  • #model-context-protocol
Tools

Feb 7, 2025 6 min read

Pi-hole + Unbound: What They Do and Why They Replace Your ISP's DNS

Pi-hole blocks ads at the DNS level. Unbound resolves queries directly against root servers. Together they keep your DNS private and local.

  • #pihole
  • #unbound
  • #dns
Tools

Feb 6, 2025 6 min read

What Is CrowdSec and How It Adds Threat Intelligence to Your Homelab

CrowdSec is an open-source security engine with crowd-sourced threat intelligence. Here is what it does, how it works, and why it replaces fail2ban.

  • #crowdsec
  • #security
  • #homelab
Tools

Feb 5, 2025 6 min read

What Is Paperless-ngx and Why Self-Host Your Documents

Paperless-ngx is an open-source document management system with OCR and full-text search. Here is why self-hosting it beats cloud alternatives.

  • #paperless-ngx
  • #documents
  • #self-hosted
Lab

Feb 4, 2025 5 min read

What Is Traefik and Why It's the Go-To Reverse Proxy for Homelabs

Traefik auto-discovers Docker services, handles TLS, and routes traffic without manual config rewrites. Here is why homelabbers pick it.

  • #traefik
  • #reverse-proxy
  • #homelab
Lab

Feb 3, 2025 5 min read

Hardening Traefik with CrowdSec forwardAuth in a Homelab Reverse-Proxy Stack

Practical homelab guide to wire Traefik forwardAuth with CrowdSec, validate it, and handle the security tradeoffs before production.

  • #traefik
  • #crowdsec
  • #homelab
Lab

Feb 2, 2025 5 min read

Secure Remote Docker Deployments with Proton Pass CLI, Docker Contexts, and SSH

Idempotent remote Docker deploys over SSH with Proton Pass CLI secrets, including the security tradeoffs and mitigations that actually matter.

  • #docker
  • #proton-pass
  • #ssh
Lab

Feb 1, 2025 4 min read

Pi-hole + Unbound Behind Traefik with a Clean /admin Redirect

How this homelab publishes Pi-hole admin via Traefik while keeping DNS local, with practical hardening steps for the risky defaults.

  • #pihole
  • #unbound
  • #traefik
Lab

Jan 31, 2025 5 min read

Running Paperless-ngx Behind Traefik with Internal Network Segmentation (Redis + Postgres)

A homelab-backed Paperless-ngx + Traefik deployment with segmented Redis/Postgres networks, concrete checks, and security hardening lessons.

  • #homelab
  • #docker
  • #paperless-ngx
Systems

Jan 30, 2025 4 min read

Durable AI-Agent Memory in a Homelab Repo with MCP Setup/Check Scripts

Use setup/check scripts and a Dockerized MCP memory server to keep agent context durable while avoiding secret leakage into repo memory.

  • #mcp
  • #ai-agents
  • #homelab
Lab

Jan 29, 2025 9 min read

Setting Up a Docker Swarm AI Agent Cluster for Security Research

Build AI agent lab on Raspberry Pi with Docker Swarm: encrypted networks, HMAC auth, and security monitoring. Production-grade patterns on $600 hardware.

  • #docker
  • #raspberry-pi
  • #ai-agents
Systems

Jan 28, 2025 10 min read

10 Lessons from Building an AI Agent Security Lab

Lab lessons: prompt injection unsolvable, vendor lock-in is operational risk, agility is control. Breaking systems teaches security faster than theory.

  • #ai-security
  • #lessons-learned
  • #hands-on
Systems

Jan 27, 2025 11 min read

AI Security Challenges We're Not Ready For

Unprepared for autonomous agents, model poisoning, deepfakes, and AI arms races. Security frameworks, certifications, and playbooks lag behind capabilities.

  • #ai-security
  • #future
  • #predictions
Doctrine

Jan 26, 2025 10 min read

From USS Tennessee to AI Security: A Cybersecurity Journey

From USS Tennessee ISSM to AI security: how traditional cybersecurity expertise became both foundation and limitation for securing AI systems.

  • #career
  • #cybersecurity
  • #ai-security
Systems

Jan 25, 2025 10 min read

How to Structure Data for AI Without Creating Security Nightmares

Balance AI context with security: structured data, sanitization, RAG, and least-privilege. Practical patterns for safe AI without data exfiltration risks.

  • #ai-security
  • #data-architecture
  • #rag
Systems

Jan 24, 2025 10 min read

Building a Multi-Model AI System for Security and Agility

Multi-model architecture with Claude, GPT-4, and GLM enables rapid provider switching, cost optimization, and protection against vendor lock-in.

  • #ai-architecture
  • #multi-model
  • #sdk
Systems

Jan 23, 2025 12 min read

Vendor Lock-In is Your Biggest AI Security Risk

Cloud AI providers control your infrastructure completely. Multi-vendor architecture isn't optional; it's a security control for operational resilience.

  • #ai-security
  • #vendor-lock-in
  • #architecture
Platform

Jan 19, 2025 3 min read

Why We Chose Astro for Our Showcase Site

Exploring Astro's islands architecture, content collections, and why it's perfect for static sites with dynamic needs.

  • #astro
  • #web-dev
  • #jamstack