<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Development on Embedinker Labs</title><link>https://lab.embedinker.com/tags/development/</link><description>Recent content in Development on Embedinker Labs</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 30 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://lab.embedinker.com/tags/development/index.xml" rel="self" type="application/rss+xml"/><item><title>Coding with Gemini: Accelerating Development in the Lab</title><link>https://lab.embedinker.com/posts/use-of-gemini-dev/</link><pubDate>Tue, 30 Jun 2026 00:00:00 +0000</pubDate><guid>https://lab.embedinker.com/posts/use-of-gemini-dev/</guid><description>&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;
&lt;p&gt;We had several attempts at using AI—either for physics problems, for trading signals, or for general-purpose fuzzy automations. They worked well. We&amp;rsquo;ll skip those here.&lt;/p&gt;
&lt;p&gt;We put significant emphasis on understanding the inner workings of the systems we build—whatever &amp;ldquo;understanding&amp;rdquo; might mean algorithmically speaking (a concept that, between Charles Peirce and logicians, remains up in the air).&lt;/p&gt;
&lt;p&gt;We also admire the recent advances in LLMs, and we plan to deploy them whenever and wherever they are truly relevant.&lt;/p&gt;</description></item></channel></rss>