<?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>Alex Ratner on TLDRecap ⏮️</title>
    <link>https://development.tldrecap.tech/presenters/alex-ratner/</link>
    <description>Recent content in Alex Ratner on TLDRecap ⏮️</description>
    <image>
      <title>TLDRecap ⏮️</title>
      <url>https://development.tldrecap.tech/images/tldrecap_logo.jpg</url>
      <link>https://development.tldrecap.tech/images/tldrecap_logo.jpg</link>
    </image>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Fri, 19 Jun 2026 09:12:29 -0700</lastBuildDate>
    <atom:link href="https://development.tldrecap.tech/presenters/alex-ratner/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Observability: Role of Evals, Benchmarks &amp; Data in Frontier AI | Alex Ratner from Snorkel AI</title>
      <link>https://development.tldrecap.tech/posts/2026/scale-ai-data/generative-ai-evaluation-gap-better-benchmarks-data/</link>
      <pubDate>Fri, 19 Jun 2026 09:12:29 -0700</pubDate>
      <guid>https://development.tldrecap.tech/posts/2026/scale-ai-data/generative-ai-evaluation-gap-better-benchmarks-data/</guid>
      <description>&lt;p&gt;&lt;strong&gt;Presenters&lt;/strong&gt;&lt;/p&gt;
&lt;ul&gt;
  &lt;li&gt;
    &lt;a href=&#34;https://development.tldrecap.tech/presenters/alex-ratner&#34;&gt;Alex Ratner&lt;/a&gt;
  &lt;/li&gt;&lt;/ul&gt;
&lt;p&gt;&lt;strong&gt;Source&lt;/strong&gt;&lt;/p&gt;
&lt;ul&gt;
  &lt;li&gt;
    &lt;a href=&#34;https://development.tldrecap.tech/sources/scale-ai-and-data-2026&#34;&gt;Scale AI and Data 2026&lt;/a&gt;
  &lt;/li&gt;&lt;/ul&gt;
&lt;h1 id=&#34;closing-the-generative-ai-evaluation-gap-building-better-benchmarks-with-smarter-data-&#34;&gt;Closing the Generative AI Evaluation Gap: Building Better Benchmarks with Smarter Data 🚀&lt;/h1&gt;
&lt;p&gt;Hey everyone! Alex Ratner here, co-founder and CEO at Snorkel. We&amp;rsquo;re a frontier
lab dedicated to building datasets and environments for evaluating, tuning, and
training AI. Today, we&amp;rsquo;re diving deep into a crucial challenge in the world of
generative AI: &lt;strong&gt;closing the evaluation gap&lt;/strong&gt;. This is absolutely central to
improving how we observe and understand AI agents.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
