<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tech on The Farah Stack</title><link>https://thefarahstack.com/tags/tech/</link><description>Recent content in Tech on The Farah Stack</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 12 Feb 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://thefarahstack.com/tags/tech/index.xml" rel="self" type="application/rss+xml"/><item><title>Debunking the 30 Total Engineers Hype at X</title><link>https://thefarahstack.com/posts/debunking-30-engineers/</link><pubDate>Thu, 12 Feb 2026 00:00:00 +0000</pubDate><guid>https://thefarahstack.com/posts/debunking-30-engineers/</guid><description>&lt;p&gt;&lt;img src="https://thefarahstack.com/images/posts/debunking-30-engineers.png" alt="Twitter to X"&gt;&lt;/p&gt;&#10;&lt;p&gt;The recent viral claims about X running on just 30 engineers have sparked a lot of celebration in certain circles, posts framing it as proof that massive layoffs + extreme leanness = superior efficiency.&lt;/p&gt;&#10;&lt;p&gt;But let&amp;rsquo;s challenge the terminology and add some missing context before everyone rushes to declare small-team supremacy the new universal truth on X.&lt;/p&gt;&#10;&lt;p&gt;&lt;strong&gt;What Nikita Bier actually said (Jan 10, 2026):&lt;/strong&gt;&lt;/p&gt;&#10;&lt;blockquote&gt;&#10;&lt;p&gt;&amp;ldquo;We only have ~30 engineers on the product but they&amp;rsquo;re the best in the business&amp;rdquo; — &lt;a href="https://x.com/nikitabier"&gt;@nikitabier&lt;/a&gt;, replying to @BillyM2k and @BoredElonMusk&lt;/p&gt;</description></item><item><title>OpenClaw: Full Danger Edition</title><link>https://thefarahstack.com/posts/openclaw-full-danger-edition/</link><pubDate>Mon, 02 Feb 2026 00:00:00 +0000</pubDate><guid>https://thefarahstack.com/posts/openclaw-full-danger-edition/</guid><description>&lt;p&gt;&lt;img src="https://thefarahstack.com/images/posts/openclaw-full-danger-edition.png" alt="OpenClaw"&gt;&lt;/p&gt;&#10;&lt;p&gt;OpenClaw is your local AI assistant that stays completely on your device with no cloud dependency. It runs on any operating system and platform, giving you full control without corporate oversight. Here is the unfiltered breakdown.&lt;/p&gt;&#10;&lt;h2 id="architecture-how-it-actually-flows"&gt;Architecture (how it actually flows)&lt;/h2&gt;&#10;&lt;pre tabindex="0"&gt;&lt;code&gt;Messaging Channels&#10;(WhatsApp • Telegram • Slack • Discord • Signal • iMessage • Teams • Matrix • Google Chat • BlueBubbles • Zalo • WebChat…)&#10; ↓&#10;┌───────────────┐&#10;│ Gateway │ ← ws://127.0.0.1:18789&#10;│ │ sessions • presence • cron • config • tool router • webhook hooks&#10;└───────┬───────┘&#10; │&#10; ┌────┼────┐&#10; │ │ │&#10;Pi/RPC CLI UI / Apps&#10;Agent openclaw ├─ WebChat (browser lifeline)&#10; ├─ Control UI (admin dashboard)&#10; ├─ macOS menu bar (quick dopamine)&#10; └─ iOS / Android nodes (mobile eyes &amp;amp; ears)&#10;&#10; │&#10; ├─→ Tools (deep system reach)&#10; │ ├─ Browser (CDP + managed Chromium – full web control)&#10; │ ├─ Canvas (A2UI agent-driven visual workspace)&#10; │ ├─ Node actions (camera live feed, screen record, notify popups, location pings…)&#10; │ ├─ Cron / webhooks / session juggling&#10; │ └─ Skills (ClawHub registry – community poison or power)&#10; │&#10; └─→ LLMs (Claude Opus preferred, OpenAI backup, local LLMs, automatic failover)&#10;&lt;/code&gt;&lt;/pre&gt;&lt;p&gt;A message arrives through any channel and gets routed to the Gateway. The Gateway decides what needs to happen next, then wakes the Pi/RPC agent or main agent. The agent uses tools and LLMs to process everything and sends the response back through the same path. It stays entirely local unless you deliberately configure remote access, which is the biggest gotcha — you will see later in the article.&lt;/p&gt;</description></item></channel></rss>