<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rex on NotNil Blog</title><link>https://notnil.org/en/tags/rex/</link><description>Recent content in Rex on NotNil Blog</description><generator>Hugo</generator><language>en-US</language><copyright>© Matthieu Moreau</copyright><lastBuildDate>Mon, 03 Feb 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://notnil.org/en/tags/rex/index.xml" rel="self" type="application/rss+xml"/><item><title>REX 2024</title><link>https://notnil.org/en/posts/23-rex2024/</link><pubDate>Mon, 03 Feb 2025 00:00:00 +0000</pubDate><guid>https://notnil.org/en/posts/23-rex2024/</guid><description>&lt;figure&gt;&lt;img src="https://notnil.org/images/posts/rex2024/feature.jpeg"&gt;&#10;&lt;/figure&gt;&#10;&#10;&lt;p&gt;1 year ago I wrote &lt;a href="https://notnil.org/en/posts/19-rexgenai/"&gt;a post&lt;/a&gt; about what we had seen / done in GenAI at &lt;a href="https://coddity.com"&gt;Coddity&lt;/a&gt; and with some clients, and had drawn some insights out of it. 1 year later, I wouldn&amp;rsquo;t change much of it (self-congratulation), but if last year I was amusing myself formulating hypotheses, some of them have turned into certainties.&lt;/p&gt;&#10;&lt;h2 id="-technical"&gt;⚙️ Technical&lt;/h2&gt;&#10;&lt;p&gt;All GenAI projects look alike and need the same components. It is essential to develop and maintain a common software foundation while avoiding &amp;ldquo;vendor lock&amp;rdquo;, so as to quickly benefit from the (numerous) new things, test them (and keep the pace).&lt;/p&gt;</description></item></channel></rss>