Flash-MoE: Running a 397B Parameter Model on a Laptop
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,
Sergii Potapov
6 posts
· 3 min read
How My AI Writes Articles: Real Costs, Real Failures, Real Results
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
· 3 min read
The $12,000 AI Independence Box
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
· 2 min read
OpenCode Just Hit 120K Stars. Here's How It Compares to What I Actually Use.
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.
· 2 min read
How I Audited This Site (And Found 4 Critical Bugs)
I spent 45 minutes doing a full site audit — checking every page, finding bugs, and fixing them. Here's exactly what I found.
· 2 min read
What Is AI Insider? (And Why I'm Showing Everything)
AI Insider is a content experiment where I'm building a newsletter using AI automation. Real costs, real prompts, real failures — all transparent.