# Practical Applications <div class="callout" data-callout="info"> <div class="callout-title">Category Overview</div> <div class="callout-content"> Hands-on guides, real-world implementations, and practical tools for AI practitioners. </div> </div> --- ## Topics Covered <div class="topic-area"> ### Setup Guides - Tool installation - Configuration - Environment setup - Integration </div> <div class="topic-area"> ### Implementation - Web development - Deployment strategies - Case studies - Workflows </div> <div class="topic-area"> ### Knowledge Management - Documentation - Publishing - Digital gardens - Content creation </div> --- ## Articles in This Category **33 articles** • Sorted by most recent <div class="latest-articles"> ### [[autoresearch-blackwell-gb10-151-experiments|AutoResearch on Blackwell GB10: 151 Experiments Overnight]] 🆕 *intermediate • 15 min read* • 2026-03-14 Running Karpathy's AutoResearch overnight on a Blackwell GB10 revealed that hardware FLOPS, not VRAM, determine optimal model architecture. 151 experiments showed surprising correlations between compute efficiency and model scaling laws, with implications for sparse models and inference optimization. ### [[controlling-your-home-from-the-terminal|Controlling Your Home From the Terminal: Home Assistant, Docker, and a Custom CLI]] *beginner • 9 min read* • 2026-02-28 How I replaced a fragmented smart home ecosystem with Home Assistant on a Raspberry Pi, built a Python CLI to control it, and connected it to Claude Code for AI-assisted home control. Covers Nest thermostat, Yale locks, Roborock vacuum, and a 13-command CLI. ### [[fixing-macos-window-chaos-hammerspoon-karabiner|Fixing macOS Window Chaos: How Hammerspoon and Karabiner Solved My Docking Nightmare]] *beginner • 8 min read* • 2026-02-20 A simple Hammerspoon config that fingerprints your display setup and auto-restores window positions when you dock or undock, with Karabiner hotkeys for manual control. Built in one Claude Code session after years of fighting Rectangle, Moom, and BetterSnapTool. ### [[when-aria-crashed-the-dgx|When ARIA Crashed the DGX: Building GPU Monitoring in 5 Minutes]] *intermediate • 12 min read* • 2026-01-17 My autonomous research system tried to allocate 260GB on a 128GB GPU and crashed the entire DGX. Here's the monitoring system I built in 5 minutes using PyTorch + PSI + Telegram to prevent it from happening again. ### [[concentric-system-analysis-with-claude|Hardening a Production System with 40 Parallel AI Agents]] *intermediate • 10 min read* • 2026-01-15 Using 40 specialized AI agents to systematically harden a Mac M4 Max, eliminating security vulnerabilities, cutting boot time 35%, resolving VPN conflicts, and unifying fragmented automation across three machines. ### [[debugging-million-token-meeting-notes|The $221 Bill: Finding and Fixing Million-Token Meeting Notes]] *intermediate • 15 min read* • 2026-01-14 How a set-and-forget meeting notes automation quietly racked up costs with 1M-token prompts, and why chunking and caching matter now that the AI honeymoon is over. ### [[mcphub-managing-mcp-servers-across-ai-tools|MCPHub: Managing MCP Servers Across Multiple AI Tools]] *intermediate • 9 min read* • 2026-01-14 A native macOS app that manages Model Context Protocol server configurations across five AI tools from a single interface. ### [[auto-updating-claude-code-cli-tools|Auto-Updating CLI Tools for Claude Code Skills]] *intermediate • 8 min read* • 2026-01-12 Build an automated system that discovers CLI dependencies from Claude Code skill metadata and keeps them updated weekly via LaunchAgent. ### [[syncing-twitter-bookmarks-to-obsidian|Auto-Sync Twitter Bookmarks to Obsidian with Bird CLI]] *intermediate • 12 min read* • 2026-01-12 Build a lightweight automation that syncs your Twitter bookmarks to Obsidian every 2 hours using Bird CLI and a simple Python script. ### [[my-personal-ai-assistant-clawdbot-seneca|My Personal AI Assistant Lives Everywhere: Building with Clawdbot]] *intermediate • 9 min read* • 2026-01-10 How I built Seneca, a personal AI assistant with memory and soul that lives across Mac, Telegram, WhatsApp, and my entire infrastructure using Clawdbot. ### [[debugging-claude-code-with-claude|Debugging Claude Code with Claude: A Meta-Optimization Journey]] *intermediate • 15 min read* • 2026-01-10 Using Claude to analyze its own debug logs and session data reveals hidden performance bottlenecks and provides a systematic approach to optimizing AI development tools. ### [[when-launchagents-attack-100-dollar-api-crash-loop|When LaunchAgents Attack: A $100 API Crash Loop Story]] *intermediate • 8 min read* • 2026-01-09 How three duplicate LaunchAgents, a port conflict, and missing cost monitoring created 4,590 restart attempts and $100 in overnight API charges. ### [[Knowledge/Blog-Obsidian/Practical Applications/claude-skills-vs-mcp-servers|Claude Skills vs MCP Servers: Why Context Efficiency Matters]] *intermediate • 12 min read* • 2025-11-06 Learn how Claude Code skills provide a lightweight alternative to MCP servers with 30% better context efficiency while maintaining flexibility. ### [[building-ai-research-night-shift|My AI Research Assistant Works the Night Shift (A Claude Code Skill Story)]] *intermediate • 10 min read* • 2025-11-06 How I built a Claude Code skill that researches AI developments overnight using intelligent automation that adapts, prevents duplicates, and provides instant answers. ### [[prompt-build-ai-landscaping-skill|Prompt for Claude Code: Build AI Landscaping Skill]] 🆕 *intermediate • 8 min read* • 2025-11-06 Copy-paste prompt for Claude Code to build a complete AI research intelligence skill with duplicate prevention, structured storage, and instant retrieval. ### [[medical-llm-fine-tuning-70-to-92-percent|How I Delegated a 9-Day Medical AI Experiment (and Learned When to Step In)]] *intermediate • 14 min read* • **DGX Lab Chronicles Part 6** • 2025-10-28 Delegating a complex 60-hour ML experiment to Claude revealed when to intervene and when to trust. Learn the decision points that turned 70% accuracy into 92.4%. ### [[dgx-lab-benchmarks-vs-reality-day-4|DGX Lab: When Benchmark Numbers Meet Production Reality - Day 4]] *intermediate • 10 min read* • **Series Part 4** • 2025-10-26 NVIDIA's DGX Spark benchmarks show 82,739 tokens/sec for training and sub-1% accuracy degradation with FP4. After 6 days of intensive ML workloads, I reveal what the benchmarks don't tell you about GPU inference failures, memory fragmentation, and production workarounds. ### [[three-days-to-build-ai-research-lab-dgx-claude|Three Days to Build an AI Research Lab: My DGX + Claude Experiment]] *intermediate • 7 min read* • **Series Part 1** • 2025-10-21 From hardware delivery to production ML experiments in 72 hours, building an AI research lab with Claude Code as a thought partner and documenting the entire journey. ### [[dgx-lab-supercharged-bashrc-ml-workflows-day-2|DGX Lab: Supercharge Your Shell with 50+ ML Productivity Aliases - Day 2]] *beginner • 10 min read* • **Series Part 2** • 2025-10-20 Transform your default shell into a productivity powerhouse with GPU monitoring shortcuts, smart aliases, and custom functions—setup in 5 minutes, benefit forever. ### [[dgx-lab-intelligent-gateway-heuristics-vs-ml-day-1|DGX Lab: When Simple Heuristics Beat ML by 95,000x - Day 1]] *intermediate • 14 min read* • **Series Part 1** • 2025-10-20 Building an intelligent AI gateway that routes requests 95,000x faster than ML while maintaining 90% accuracy—proving that smart heuristics can outperform deep learning. ### [[syncing-claude-code-configs-across-machines|Syncing Claude Code Configurations Across Multiple Machines: A Practical Guide]] *intermediate* • 15 min • 2025-10-20 Learn how to intelligently sync Claude Code configurations across Mac, Pi, and DGX boxes while preserving machine-specific settings like model endpoints and API keys. ### [[building-production-ml-workspace-part-5-collaboration|Building a Production ML Workspace: Part 5 - Team Collaboration and Workflow Integration]] 🎉 *intermediate • 14 min read* • **Series Part 5/5 - Complete!** Complete your production ML workspace with team collaboration patterns, workflow automation, version control strategies, and integration frameworks that scale. ### [[building-production-ml-workspace-part-4-agents|Building a Production ML Workspace: Part 4 - Production-Ready AI Agent Templates]] *intermediate • 10 min read* • **Series Part 4/5** Build production-ready AI agents with standardized templates, tool integration patterns, comprehensive testing, and deployment readiness frameworks. ### [[building-production-ml-workspace-part-3-experiments|Building a Production ML Workspace: Part 3 - Experiment Tracking and Reproducibility]] *intermediate • 12 min read* • **Series Part 3/5** Master experiment tracking with MLflow, implement reproducible workflows, and build structured systems for managing ML research that scales from prototype to production. ### [[building-production-ml-workspace-part-2-documentation|Building a Production ML Workspace: Part 2 - Documentation Systems That Scale]] *beginner • 7 min read* • **Series Part 2/5** Build a three-tier documentation system that captures ML work for debugging, review, and blog content—turning your experiments into shareable knowledge. ### [[building-production-ml-workspace-part-1-structure|Building a Production ML Workspace: Part 1 - Designing an Organized Structure]] *beginner • 8 min read* • **Series Part 1/5** Learn how to design a scalable ML workspace structure that handles Ollama models, fine-tuning, agents, and experiments without becoming chaotic. ### [[roo-code-codebase-indexing-free-setup|Supercharging Code Discovery: My Journey with Roo Code's Free Codebase Indexing]] *beginner • 12 min read* Set up professional-grade semantic code search using Roo Code's codebase indexing with completely free tools - Qdrant Cloud and Google Gemini. ### [[unlocking-ai-value-with-prompt-engineering|Unlock AI's Full Potential: Why Prompt Engineering is Your Business Superpower]] *beginner • 4 min read* Master prompt engineering techniques to unlock better, more reliable AI outputs that drive real business results. ### [[elevating-prompt-engineering-with-integrated-tools|Elevating Prompt Engineering with Integrated Tools]] *intermediate • 6 min read* Building integrated prompt refinement tools transforms how developers interact with LLMs, streamlining workflows through concept elevation. ### [[hybrid-deployment-vercel-render-digitalocean|Deployment Dilemma: When to Use Vercel, Render, or Digital Ocean for React/Python Apps]] *intermediate • 7 min read* Practical guide to choosing the right deployment platform for React/Python applications across Vercel, Render, and Digital Ocean. ### [[cline-roo-code-quick-start|Cline and Roo Code: Quick Start Guide]] *beginner • 10 min read* Get started with Cline and Roo Code AI coding agents in VS Code, covering installation, features, and optimization techniques. ### [[roo-code-github-copilot-setup|How to Set Up Roo Code with GitHub Copilot: A Technical Guide]] *beginner • 3 min read* Step-by-step guide for setting up Roo Code with GitHub Copilot, leveraging Claude 3.7 Sonnet while maintaining enterprise compliance. ### [[transforming-research-into-interactive-app|Transforming AI Research into an Interactive Web Application: A Case Study]] *intermediate • 3 min read* Transform complex AI research output into an interactive web application using modern web technologies and Roo Code. ### [[obsidian-publish-article-garden|Creating a Technical Article Garden with Obsidian Publish]] *beginner • 4 min read* Learn how to set up Obsidian Publish for technical documentation and create an interconnected knowledge base that grows over time. </div> --- ## Navigation ### Browse Content - [[Index/by-tag|Browse by Tag]] - [[By Date|Browse by Date]] - [[Index/by-difficulty|Browse by Difficulty]] - [[Index/by-topics|Browse by Topics]] - [[Reading Paths|Learning Paths]] ### Other Categories - [[⌂ AI Development & Agents|AI Development & Agents]] - [[⌂ Cutting-Edge AI|Cutting-Edge AI]] - [[⌂ AI Systems & Architecture|AI Systems & Architecture]] - [[⌂ Emerging Trends|Emerging Trends]] ### Home - [[⌂ Home|Back to Home]]