- AI Harness Engineering: Governing & Orchestrating Agents
Explore AI Harness Engineering - designing infrastructure, context management, tool sandboxing, and evaluation loops for reliable AI agents.
4 min🇺🇸 English - Common Neural Processing Units in 2026
Overview of the most popular Neural Processing Units: Apple ANE, Intel NPU, AMD XDNA, Qualcomm Hexagon, Google TPU, Samsung Exynos and MediaTek APU.
3 min🇺🇸 English - Demystifying Infrastructure as Code: Terraform Deep Dive
Explore Infrastructure as Code (IaC) with Terraform, core concepts, Core vs. Providers architecture, and why it is essential for modern DevOps teams.
3 min🇺🇸 English - GeoLibre — A Free, Cloud-Native GIS for Every Platform
GeoLibre: an open-source GIS for web, desktop, Android, and Jupyter. Process 700+ GIS tools in the browser with MapLibre, DuckDB-WASM, and deck.gl.
4 min🇺🇸 English - jcode — RAM-Efficient AI Coding Agent for the Terminal
jcode: open-source AI coding agent for the terminal in Rust. Uses 27MB RAM vs 386MB for Claude Code, boots in 14ms, with durable memory and swarm.
4 min🇺🇸 English - MXFP4/MXFP8 Quantization — Running LLMs Locally
MXFP4/MXFP8 is the new 4-bit quantization standard for LLMs. Enables 120B-param models on a single 80GB GPU via llama.cpp and vLLM.
3 min🇺🇸 English - Run Shell Commands in JavaScript with Bun Shell
Learn how to run cross-platform shell commands directly in JavaScript and TypeScript using built-in Bun Shell.
1 min🇺🇸 English - Training on Apple Neural Engine with Private APIs
ANE project reverse-engineers Apple Neural Engine private APIs to train transformers directly on ANE — no CoreML, no GPU, no Metal.
3 min🇺🇸 English
Back
Blog
🇺🇸EnglishShowing 8 of 203 postsView all by year →