Editorial dispatches on AI systems, infrastructure, and operational craft.https://subdepthtech.com/en-ushttps://subdepthtech.com/posts/tmux-ghostty-terminal-workflow/https://subdepthtech.com/posts/tmux-ghostty-terminal-workflow/A layered guide to tmux and Ghostty, from first install to floating popups, vim navigation, and a polished dark theme.Sat, 28 Mar 2026 00:00:00 GMThomelabtmuxghosttyterminaldotfilesproductivityvimSubDepthTechhttps://subdepthtech.com/posts/ai-tooling-revolution-harnesses-models-real-risks/https://subdepthtech.com/posts/ai-tooling-revolution-harnesses-models-real-risks/The real AI risks are not about capability. They are critical thinking erosion, organizational inertia, and a misunderstanding of both AI and security.Sat, 21 Mar 2026 00:00:00 GMTaiai-agentsclaude-codecodexopinionrisk-managementcybersecurityai-toolingcritical-thinkingSubDepthTechhttps://subdepthtech.com/posts/build-your-own-ai-assistant-starter-kit-with-claude/https://subdepthtech.com/posts/build-your-own-ai-assistant-starter-kit-with-claude/A starter kit of markdown files that turns Claude into a personalized work assistant -- no coding, no setup, just conversation.Sat, 21 Mar 2026 00:00:00 GMTaiclaudeai-assistantstarter-kitproductivityclaude-mdmarkdownbeginnersSubDepthTechhttps://subdepthtech.com/posts/containerize-claude-code-codex-gemini-homelab/https://subdepthtech.com/posts/containerize-claude-code-codex-gemini-homelab/Containerize AI CLI tools with Docker for remote SSH access and OpenAI-compatible APIs via Traefik. Vendor-independent, reproducible.Thu, 12 Feb 2026 00:00:00 GMThomelabclaude-codecodexgeminidockerhomelabai-agentstraefikmulti-modelSubDepthTechhttps://subdepthtech.com/posts/i-monitored-chinese-ai-model-for-bias/https://subdepthtech.com/posts/i-monitored-chinese-ai-model-for-bias/GLM 4.6 monitoring revealed 12% geographic bias, narrative injection, and trust-building patterns. Empirical security research on lower-cost AI model behavior.Sat, 22 Nov 2025 00:00:00 GMTaiai-securitybias-detectionresearchglmchinamodel-monitoringSubDepthTechhttps://subdepthtech.com/posts/prompt-injection-the-sql-injection-of-ai/https://subdepthtech.com/posts/prompt-injection-the-sql-injection-of-ai/Prompt injection is the defining LLM vulnerability with no parameterized query fix. Unlike SQL injection, it may be theoretically impossible to solve.Fri, 21 Nov 2025 00:00:00 GMTaiai-securityprompt-injectionvulnerabilitiesllmowaspSubDepthTechhttps://subdepthtech.com/posts/why-ai-security-broke-traditional-infosec-playbooks/https://subdepthtech.com/posts/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.Thu, 20 Nov 2025 00:00:00 GMTaiai-securityinfoseccisspcareercybersecuritySubDepthTechhttps://subdepthtech.com/posts/mcp-model-context-protocol-explained/https://subdepthtech.com/posts/mcp-model-context-protocol-explained/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.Sat, 08 Feb 2025 00:00:00 GMTaimcpai-agentsmodel-context-protocolautomationSubDepthTechhttps://subdepthtech.com/posts/pihole-unbound-explained-dns-privacy/https://subdepthtech.com/posts/pihole-unbound-explained-dns-privacy/Pi-hole blocks ads at the DNS level. Unbound resolves queries directly against root servers. Together they keep your DNS private and local.Fri, 07 Feb 2025 00:00:00 GMTtoolspiholeunbounddnsprivacyhomelabSubDepthTechhttps://subdepthtech.com/posts/what-is-crowdsec-homelab-threat-intelligence/https://subdepthtech.com/posts/what-is-crowdsec-homelab-threat-intelligence/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.Thu, 06 Feb 2025 00:00:00 GMTtoolscrowdsecsecurityhomelabthreat-intelligenceidsSubDepthTechhttps://subdepthtech.com/posts/what-is-paperless-ngx-self-hosted-documents/https://subdepthtech.com/posts/what-is-paperless-ngx-self-hosted-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.Wed, 05 Feb 2025 00:00:00 GMTtoolspaperless-ngxdocumentsself-hostedhomelabSubDepthTechhttps://subdepthtech.com/posts/what-is-traefik-homelab-reverse-proxy/https://subdepthtech.com/posts/what-is-traefik-homelab-reverse-proxy/Traefik auto-discovers Docker services, handles TLS, and routes traffic without manual config rewrites. Here is why homelabbers pick it.Tue, 04 Feb 2025 00:00:00 GMThomelabtraefikreverse-proxyhomelabdockernetworkingSubDepthTechhttps://subdepthtech.com/posts/traefik-crowdsec-forwardauth-homelab/https://subdepthtech.com/posts/traefik-crowdsec-forwardauth-homelab/Practical homelab guide to wire Traefik forwardAuth with CrowdSec, validate it, and handle the security tradeoffs before production.Mon, 03 Feb 2025 00:00:00 GMThomelabtraefikcrowdsechomelabreverse-proxydockersecurityforwardauthSubDepthTechhttps://subdepthtech.com/posts/remote-docker-deploy-with-proton-pass/https://subdepthtech.com/posts/remote-docker-deploy-with-proton-pass/Idempotent remote Docker deploys over SSH with Proton Pass CLI secrets, including the security tradeoffs and mitigations that actually matter.Sun, 02 Feb 2025 00:00:00 GMThomelabdockerproton-passsshhomelabdevopssecuritySubDepthTechhttps://subdepthtech.com/posts/pihole-unbound-traefik-admin-redirect/https://subdepthtech.com/posts/pihole-unbound-traefik-admin-redirect/How this homelab publishes Pi-hole admin via Traefik while keeping DNS local, with practical hardening steps for the risky defaults.Sat, 01 Feb 2025 00:00:00 GMThomelabpiholeunboundtraefikhomelabdnssecuritydockerSubDepthTechhttps://subdepthtech.com/posts/paperless-ngx-network-segmentation-homelab/https://subdepthtech.com/posts/paperless-ngx-network-segmentation-homelab/A homelab-backed Paperless-ngx + Traefik deployment with segmented Redis/Postgres networks, concrete checks, and security hardening lessons.Fri, 31 Jan 2025 00:00:00 GMThomelabhomelabdockerpaperless-ngxtraefiksecuritypostgresredisSubDepthTechhttps://subdepthtech.com/posts/mcp-memory-contract-for-homelab-agents/https://subdepthtech.com/posts/mcp-memory-contract-for-homelab-agents/Use setup/check scripts and a Dockerized MCP memory server to keep agent context durable while avoiding secret leakage into repo memory.Thu, 30 Jan 2025 00:00:00 GMTaimcpai-agentshomelabmemoryautomationsecuritySubDepthTechhttps://subdepthtech.com/posts/docker-swarm-ai-agent-cluster-security-research/https://subdepthtech.com/posts/docker-swarm-ai-agent-cluster-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.Wed, 29 Jan 2025 00:00:00 GMThomelabdockerraspberry-piai-agentstutorialhomelabswarmSubDepthTechhttps://subdepthtech.com/posts/ten-lessons-building-ai-agent-security-lab/https://subdepthtech.com/posts/ten-lessons-building-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.Tue, 28 Jan 2025 00:00:00 GMTaiai-securitylessons-learnedhands-onlabbest-practicesSubDepthTechhttps://subdepthtech.com/posts/ai-security-challenges-not-ready-for/https://subdepthtech.com/posts/ai-security-challenges-not-ready-for/Unprepared for autonomous agents, model poisoning, deepfakes, and AI arms races. Security frameworks, certifications, and playbooks lag behind capabilities.Mon, 27 Jan 2025 00:00:00 GMTaiai-securityfuturepredictionsautonomous-agentschallengesSubDepthTechhttps://subdepthtech.com/posts/from-uss-tennessee-to-ai-security/https://subdepthtech.com/posts/from-uss-tennessee-to-ai-security/From USS Tennessee ISSM to AI security: how traditional cybersecurity expertise became both foundation and limitation for securing AI systems.Sun, 26 Jan 2025 00:00:00 GMTlearningcareercybersecurityai-securitypersonalissmcisspSubDepthTechhttps://subdepthtech.com/posts/structure-data-for-ai-without-security-nightmares/https://subdepthtech.com/posts/structure-data-for-ai-without-security-nightmares/Balance AI context with security: structured data, sanitization, RAG, and least-privilege. Practical patterns for safe AI without data exfiltration risks.Sat, 25 Jan 2025 00:00:00 GMTaiai-securitydata-architectureragvector-databasessanitizationSubDepthTechhttps://subdepthtech.com/posts/building-multi-model-ai-system/https://subdepthtech.com/posts/building-multi-model-ai-system/Multi-model architecture with Claude, GPT-4, and GLM enables rapid provider switching, cost optimization, and protection against vendor lock-in.Fri, 24 Jan 2025 00:00:00 GMTaiai-architecturemulti-modelsdkclaudeopenaiagilitySubDepthTechhttps://subdepthtech.com/posts/vendor-lock-in-biggest-ai-security-risk/https://subdepthtech.com/posts/vendor-lock-in-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.Thu, 23 Jan 2025 00:00:00 GMTaiai-securityvendor-lock-inarchitecturestrategymulti-cloudSubDepthTechhttps://subdepthtech.com/posts/building-with-astro/https://subdepthtech.com/posts/building-with-astro/Exploring Astro's islands architecture, content collections, and why it's perfect for static sites with dynamic needs.Sun, 19 Jan 2025 00:00:00 GMTwebastroweb-devjamstackSubDepthTech