**TL;DR:** Yesterday I wrote about running 400B models on a laptop. Today someone did it on an iPhone. The AI democratization curve is steeper than anyone expected — and it's changing how I think about building AI agents.
TL;DR: A new Mixture-of-Experts implementation lets you run a 397 billion parameter model on consumer hardware. No cloud. No API costs. Just your laptop and patience.
The Breakthrough
Yesterday,
TL;DR: I run an AI writing operation that publishes daily content. Here's exactly how it works — the prompts, the costs ($0.08/article), the spectacular failures, and
TL;DR: George Hotz's tiny corp is now shipping tinybox — a $12,000 computer that runs 120B parameter models offline. No API costs. No rate limits. No data
OpenCode is the hot new AI coding agent (608 points on HN today). I tested it against Claude Code, Cook, and OpenClaw. Here's which one I actually use daily.
Cook is a CLI that adds review loops, parallel racing, and task progression to Claude Code. It solves the one-shot prompt problem with systematic iteration.