<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM on Advancing Engineering</title><link>https://www.advancingengineering.dev/tags/llm/</link><description>Recent content in LLM on Advancing Engineering</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 10 May 2026 21:30:30 +0100</lastBuildDate><atom:link href="https://www.advancingengineering.dev/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM Wiki: The Knowledge Base That Maintains Itself</title><link>https://www.advancingengineering.dev/posts/2026-03-llm-wiki/</link><pubDate>Tue, 10 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.advancingengineering.dev/posts/2026-03-llm-wiki/</guid><description>&lt;p&gt;Of course you&amp;rsquo;ve got document stores. But be honest, how much ongoing love do they all have? Is every one of your onboarding guides on point, and how many of the &amp;ldquo;current architecture&amp;rdquo; diagrams show databases that were deprecated before you joined?&lt;/p&gt;</description></item><item><title>LLM Permissions: speed *and* safety in Practice</title><link>https://www.advancingengineering.dev/posts/2026-02-permissions/</link><pubDate>Tue, 10 Feb 2026 00:00:00 +0000</pubDate><guid>https://www.advancingengineering.dev/posts/2026-02-permissions/</guid><description>&lt;p&gt;93% of LLM permission requests are approved. That number should make you uncomfortable.
Not because approving is wrong — most of those approvals are fine — but because a 93% approval rate is a signal that you haven&amp;rsquo;t designed your permission model. You&amp;rsquo;ve just been clicking through dialogs.&lt;/p&gt;
&lt;p&gt;There&amp;rsquo;s also the opposite problem: leaving an agent to work autonomously, then coming back to find it paused, waiting for you to confirm that yes, it can &lt;code&gt;grep&lt;/code&gt; a file it&amp;rsquo;s been reading all session. Both failures have the same root cause: permissions set by default, not design.&lt;/p&gt;
&lt;p&gt;The question worth sitting with is whether you can move faster &lt;em&gt;and&lt;/em&gt; sleep better. The answer is yes, but it requires deliberate thought about what your LLM actually needs to do its job.&lt;/p&gt;</description></item></channel></rss>