-
RAG on Your Own Notes — Build a Second Brain That Actually Answers
How to build local RAG over your personal notes on a Mac — Obsidian with a community AI plugin and Ollama, AnythingLLM, and Open WebUI compared, plus chunking, embedding models, and honest limits.
-
Local LLMs with Ollama: Pairing Ollama with Continue or Cline for a private IDE
A field-tested take on pairing Ollama with Continue or Cline for a private IDE with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
What Your Phone Knows About You in a Single Day
Your phone collects thousands of data points daily. This data-driven investigation reveals exactly what your device knows about you—location, behavior.
-
The Ghost in the Machine: What AI Hallucinations Reveal About Intelligence
AI hallucinations are structural, not fixable bugs — understanding why reveals something profound about the nature of knowledge and language itself.
-
The Hidden macOS AI Features Apple Shipped Quietly
A power-user tour of the on-device AI built into macOS — Live Text OCR, Visual Look Up, semantic photo search, background removal, voice isolation, offline dictation, and Spotlight ML — with a trick for each.
-
Agentic coding: What to log when an agent writes for you
A field-tested take on what to log when an agent writes for you with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
The End of Passwords Is Closer Than You Think: The World After Passkeys
Passwords are dying. Passkeys offer a better future—more secure, easier to use, and phishing-resistant. Learn how they work and how to start using them today.
-
How the Pentagon's Budget Quietly Shapes Every AI Tool You Use
DARPA created the internet, GPS, and early AI. How defense funding shapes civilian AI reveals the true incentive structure behind the tools everyone uses daily.
-
Your Mac Studio Can Replace a $1,500/Month AI API Bill
When does a Mac Studio running local LLMs beat paying OpenAI or Anthropic per token? Break-even math, latency benchmarks, Ollama and MLX server setups, and the hybrid pattern for indie developers.
-
MCP servers: Treating MCP servers as a supply chain, not a side project
A field-tested take on treating MCP servers as a supply chain, not a side project with MCP servers: what it rewards, where it breaks, and how to keep the workflow honest.
-
How to Build a Personal AI Assistant Without a Single Line of Code
Learn how to build a personalized AI assistant without writing code. This practical tutorial covers platform selection, knowledge bases, automation, and.
