-
The Mac Terminal Commands That Unlock Hidden AI Power
Power-user macOS terminal commands for local AI: Ollama CLI flags, Modelfiles, OLLAMA_KEEP_ALIVE, pbpaste one-liners, Simon Willison's llm tool, jq parsing, and shell aliases for AI tasks.
-
Local LLMs with Ollama: Running evals locally before trusting a new model
A field-tested take on running evals locally before trusting a new model with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Why Most Smart Products Actually Get Dumber After a Year of Use
Discover why your smart home devices, fitness trackers, and connected gadgets seem to lose intelligence over time. From software bloat to planned.
-
What We Got Wrong About AI in the First Half of 2026: A Mid-Year Reckoning
A mid-2026 reckoning on AI predictions: what the conventional wisdom got badly wrong, what surprised everyone, and how to read AI coverage more critically.
-
What's Coming Next for AI on Mac — and How to Be Ready
Where on-device AI on Apple Silicon is heading: shrinking open models, rising memory bandwidth, Apple's Foundation Models framework, agentic AI, and local multimodality. Practical advice on hardware, skills, and the local AI stack to be ready.
-
Agentic coding: Planning outputs as the real product of the first turn
A field-tested take on planning outputs as the real product of the first turn with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
Monthly Retrospective: What Technology Taught Us in June 2026
June 2026 brought AI maturation, disappearing technologies, productivity wisdom, and the eternal debate between open and closed systems. Here's what we learned.
-
The Attention Economy Was Just the Prototype. AI Is the Real Thing.
Social media's dopamine loops were the first generation of algorithmic influence. Conversational AI represents a qualitative leap in the capacity to shape human behavior.
-
The 7 AI Mistakes Mac Power Users Keep Making
Seven common local LLM mistakes on Mac and how to fix them. Covers Ollama context length, quantization tradeoffs, VRAM limits on Apple Silicon, swap death spirals, Modelfiles, and hybrid cloud-local routing with exact commands.
-
MCP servers: Testing MCP servers with a plain JSON-RPC client first
A field-tested take on testing MCP servers with a plain JSON-RPC client first with MCP servers: what it rewards, where it breaks, and how to keep the workflow honest.
-
What the Ideal Home Office Looks Like According to Science
Science reveals what makes home offices effective: lighting, temperature, acoustics, ergonomics, and psychology. Build a workspace that works as hard as you do.
