Articles

How to Access Apple’s Hidden 3B LLM on Your Mac

H

Your Apple Silicon Mac already has a 3-billion parameter language model sitting on disk, locked behind Siri. Apfel by Arthur-Ficia is a native Swift project that wraps Apple’s on-device Foundation Model into a CLI tool and an OpenAI-compatible HTTP server. No API keys, no cloud, no per-token costs. It runs entirely on your Neural Engine. Apfel GitHub repository homepage What Is Apfel? Apfel...

How to Track Satellites and Decode Signals Locally with Ground Station

H

Ground Station GitHub repository homepage What caught my attention wasn’t what it claims to do, it’s what it does instead of three different tools I was already juggling. Someone just open-sourced a full suite for tracking satellites and decoding their radio signals locally. You don’t even need the internet. It uses an SDR to pull weather images and raw data straight from space...

How to Use GeForce NOW with Zero Telemetry Using OpenNOW

H

What Is OpenNOW? OpenNOW is a reverse-engineered, open-source desktop client for NVIDIA’s GeForce NOW cloud gaming service. Unlike the official GeForce NOW application, which is closed-source and includes various telemetry and background tracking, OpenNOW provides complete transparency about what it does while maintaining full compatibility with NVIDIA’s streaming infrastructure...

How to Self-Host a Collaborative Travel Planner with TREK

H

TREK is a self-hosted travel planner that puts your itinerary, maps, budget, and packing lists in one place. You can share it with travel companions, collaborate in real time, and install it directly on your phone without the App Store. It runs on your own server, so your data stays yours. TREK GitHub repository homepage The drag-and-drop itinerary builder makes trip planning intuitive...

CL1 LLM Encoder: Biological Neurons Control AI Token Generation

C

Cortical Labs built a biological computer called CL1 with 200,000 living human neurons. An independent developer wired those neurons into a local LLM. The cells now influence which tokens the AI generates. It challenges everything we assume about AI hardware. CL1 LLM Encoder GitHub repository homepage The CL1 sells for $35,000 and runs neurons in a nutrient solution. Cortical Labs taught it to...

Get in touch

Quickly communicate covalent niche markets for maintainable sources. Collaboratively harness resource sucking experiences whereas cost effective meta-services.