<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Signal on Bil Arikan</title><link>https://bil.arikan.ca/tags/signal/</link><description>Recent content in Signal on Bil Arikan</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Thu, 28 May 2026 00:00:00 -0500</lastBuildDate><atom:link href="https://bil.arikan.ca/tags/signal/index.xml" rel="self" type="application/rss+xml"/><item><title>Local AI Lab --- Setting Up OpenClaw as a Personal AI Gateway</title><link>https://bil.arikan.ca/posts/local-ai-lab-setting-up-openclaw/</link><pubDate>Thu, 28 May 2026 00:00:00 -0500</pubDate><guid>https://bil.arikan.ca/posts/local-ai-lab-setting-up-openclaw/</guid><description>&lt;p&gt;At this point in the series, the inference layer is done. CT 100 is running llama-server on the RTX 5060 Ti at 26 T/s. CT 101 is running llama-server on the RX 6650 XT at 51 T/s. Both expose OpenAI-compatible endpoints on the local network.&lt;/p&gt;</description></item></channel></rss>