The era of needing to send every query to a cloud API is ending. Modern Apple Silicon ships with enough unified memory and neural engine throughput to run 12-billion-parameter language…
Why Clicking “Open in GitHub Desktop” Opens the Wrong App — and How to Fix It
If you’ve ever clicked “Open with GitHub Desktop” on a GitHub repo page and watched the wrong app launch — SourceTree, Fork, or something else entirely — you’re not alone. This is a macOS…
Binance Signal Engine — an OpenClaw skill that brings crypto trading signal generation to AI agents
Just published my first skill on ClawHub: Binance Signal Engine — an OpenClaw skill that brings crypto trading signal generation to AI agents. I’ve been doing these Binance signal workflows manually for…
Get good at setting rules for your AI dev tools
https://merowing.info/posts/stop-getting-average-code-from-your-llm/https://agents.md Sure, one day, AI agents will be good at self reinforcement, recursive improvement, etc, all towards singularity without eating up all your credits/money overnight. But until then, help the…
Remove bloatware for Win 11 and 10
https://github.com/Raphire/Win11Debloat Just got around to sort this out. I only use my spare Win 11 computer for watching YouTube and stock/crypto charts, but still don’t like having other bloatware installed….
The 2026 Beginner’s Guide to Prompt Engineering for Professionals
What Has Changed (And Why You Should Care) If you’ve been using chatbots like ChatGPT, Claude, or Gemini for basic questions and answers, you’re only scratching the surface of what…
Good to have a USB recovery tool ready, particularly if you don’t have a spare PC at home
https://www.makeuseof.com/ultimate-rescue-usb-can-save-any-windows-pc Keep one of these in your drawer, just in case you will ever need to do a full recovery or rescue.
How to Securely Access Ollama and Swama Remotely on macOS with Caddy
Run two local AI runtimes behind a single secure reverse proxy with separate authentication Running Ollama or Swama locally is straightforward: start the server and connect via localhost. But if…
Swama vs Ollama: Why Apple Silicon Macs Deserve a Faster Local AI Runtime
The reason is simple: because you can — and even faster now. If you have an Apple Silicon Mac (M1 or later) with 16GB of RAM or more, you can run powerful LLMs…
Metal toolchain error in Xcode 26.2
https://codeberg.org/ctietze/metal-toolchain-launchd-automounthttps://christiantietze.de/posts/2026/01/manually-mount-metal-toolchain/ If you are having problems with compiling code with Metal toolchain and can’t fix it by following install instruction in the error message “xcodebuild -downloadComponent MetalToolchain”, try to manually…
Master Video Downloads on macOS: Right-Click Any URL with yt-dlp & Automator
Introduction Video downloading on macOS can be frustrating. iTubeGo requires clicking through dialogs; other tools are bloated or unreliable. But what if you could simply right-click on any URL and…
How to Bulk Update GitHub Repository Topics (Tags) Using cURL and Bash Scripts
Automate GitHub topic updates! This tutorial shows how to efficiently bulk-update repository topics using cURL and Bash scripts, saving time and streamlining your workflow.