<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Ginigen Edge AI News</title><link>https://ginigen-ai-edge-ai-news.static.hf.space/</link><description>News and engineering notes on edge AI: running LLMs on phones and laptops, quantization, GGUF and safe on-device assistants.</description><item><title>Offline AI on a Phone: Thread Pinning, Lazy Loading, and a Safety Gate That Knows When to Stay Quiet</title><link>https://ginigen-ai-edge-ai-news.static.hf.space/a/offline-ai-on-a-phone-thread-pinning-lazy-loading-safety-gate.html</link><guid>https://ginigen-ai-edge-ai-news.static.hf.space/a/offline-ai-on-a-phone-thread-pinning-lazy-loading-safety-gate.html</guid><description>Lessons from shipping HeliGO, an offline disaster app with an on-device 4B model: thread counts, lazy loading, and safe refusals.</description><pubDate>2026-10-05T18:00:00+09:00</pubDate></item></channel></rss>