Apr 16 · 7 min read · You've got a 1.7 billion parameter model. You want it running locally. In a browser tab. No server, no API keys, no Docker containers. Sounds impossible, right? A few months ago, I would've agreed with you. But 1-bit quantized models like Bonsai 1.7B...
Join discussion
Apr 6 · 6 min read · Four days ago, Google released Gemma 4 under Apache 2.0. The headline models are the 31B dense and 26B MoE variants that compete with Llama on Arena AI. But the models I've been running nonstop since release are the ones nobody is talking about: Gemm...
Join discussion
Mar 25 · 2 min read · The Problem I Want to Solve Recruiters pay $0.05-$0.20 per document to cloud parsing services like DaXtra, RChilli, and Affinda. Beyond cost, there's a privacy issue: candidate data leaves the device and travels to vendor servers. I want to explore w...
Join discussionFeb 13 · 5 min read · No external software, no cloud, no complexity—just install and start chatting. TL;DR: I built a Chrome extension that runs Llama, DeepSeek, Qwen, and other LLMs entirely in-browser. No server, no Ollama, no API keys. Here's the full story—why I built...
Join discussion
Feb 8 · 21 min read · What We're Learning Color is one of the most powerful tools in your graphics arsenal. So far, we've worked with basic color operations - sampling textures, mixing colors, and applying simple lighting. But there's a whole world of advanced color manip...
Join discussion
Feb 2 · 20 min read · What We're Learning So far in this series, every fragment we've processed has been drawn to the screen. We've colored them, textured them, and lit them - but we've always drawn them. What if you don't want to draw certain fragments at all? What if yo...
Join discussion
Jan 25 · 23 min read · What We're Learning So far in this series, we've worked with mathematical functions like sine waves, smooth gradients, and geometric patterns. These are powerful, but they all share a common limitation: they are too perfect. Nature isn't perfectly re...
Join discussion
