<?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>Latent-Space on Intelligent Artifact</title>
    <link>https://intelligentartifact.com/tags/latent-space/</link>
    <description>Recent content in Latent-Space on Intelligent Artifact</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 16 Nov 2026 13:38:03 -0800</lastBuildDate>
    <atom:link href="https://intelligentartifact.com/tags/latent-space/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Black Forest Labs turns image generation into editable workflows</title>
      <link>https://intelligentartifact.com/posts/black-forest-labs-editable-image-workflows/</link>
      <pubDate>Mon, 16 Nov 2026 13:38:03 -0800</pubDate>
      <guid>https://intelligentartifact.com/posts/black-forest-labs-editable-image-workflows/</guid>
      <description>Andreas Blattmann and Dustin Podell explain how targeted data unlocked FLUX Kontext, what SDXL taught them, and where robot learning still falls short.</description>
    </item>
    <item>
      <title>Designing software agents can actually use</title>
      <link>https://intelligentartifact.com/posts/resend-designing-software-agents-can-use/</link>
      <pubDate>Tue, 10 Nov 2026 12:05:17 -0800</pubDate>
      <guid>https://intelligentartifact.com/posts/resend-designing-software-agents-can-use/</guid>
      <description>Resend’s Zeno Rocha explains readable pricing, remote tool permissions, and why winning a recommendation differs from completing an agent’s task.</description>
    </item>
    <item>
      <title>Handshake shows where professional AI agents still fail</title>
      <link>https://intelligentartifact.com/posts/handshake-professional-ai-agent-failures/</link>
      <pubDate>Mon, 09 Nov 2026 09:15:53 -0800</pubDate>
      <guid>https://intelligentartifact.com/posts/handshake-professional-ai-agent-failures/</guid>
      <description>Inside Handshake’s scientific-image tests, simulated banks and safety evaluations, where polished outputs hide costly mistakes.</description>
    </item>
    <item>
      <title>Stanford makes coding-agent students answer to real maintainers</title>
      <link>https://intelligentartifact.com/posts/stanford-coding-agents-real-maintainer-feedback/</link>
      <pubDate>Sun, 08 Nov 2026 13:23:29 -0800</pubDate>
      <guid>https://intelligentartifact.com/posts/stanford-coding-agents-real-maintainer-feedback/</guid>
      <description>Mihail Eric connects Stanford’s coding-agent curriculum with Monaco’s internal tools, showing why mentorship, verification, and human judgment matter.</description>
    </item>
    <item>
      <title>Jamin Ball connects Anthropic’s IPO to the cost of compute</title>
      <link>https://intelligentartifact.com/posts/anthropic-ipo-compute-financing-jamin-ball/</link>
      <pubDate>Fri, 06 Nov 2026 21:49:28 -0500</pubDate>
      <guid>https://intelligentartifact.com/posts/anthropic-ipo-compute-financing-jamin-ball/</guid>
      <description>Jamin Ball explains how Anthropic’s proposed IPO connects financial disclosure, GPU financing, model economics, and the cost of staying competitive.</description>
    </item>
    <item>
      <title>Fabian Theis wants cell models to choose the next experiment</title>
      <link>https://intelligentartifact.com/posts/fabian-theis-cell-models-next-experiment/</link>
      <pubDate>Fri, 06 Nov 2026 07:10:53 -0800</pubDate>
      <guid>https://intelligentartifact.com/posts/fabian-theis-cell-models-next-experiment/</guid>
      <description>Fabian Theis explains how virtual-cell research can connect biological maps, intervention predictions, and repeated laboratory experiments.</description>
    </item>
    <item>
      <title>Swyx on rebuilding SaaS and putting Jev inside software</title>
      <link>https://intelligentartifact.com/posts/swyx-rebuilding-saas-jev-software/</link>
      <pubDate>Wed, 04 Nov 2026 05:32:51 -0500</pubDate>
      <guid>https://intelligentartifact.com/posts/swyx-rebuilding-saas-jev-software/</guid>
      <description>Swyx explains why his conference team rebuilt SaaS tools, what its AI judge missed, and how Jev could put narrow model decisions inside ordinary software.</description>
    </item>
    <item>
      <title>Warp puts coding agents inside a measurable workflow</title>
      <link>https://intelligentartifact.com/posts/warp-coding-agents-measurable-workflow/</link>
      <pubDate>Tue, 03 Nov 2026 15:16:25 -0500</pubDate>
      <guid>https://intelligentartifact.com/posts/warp-coding-agents-measurable-workflow/</guid>
      <description>Zach Lloyd demonstrates Warp’s shared agent workflows, scoring and benchmarks, and explains which self-improvement capabilities remain future work.</description>
    </item>
    <item>
      <title>How Legora tests agents without reading client work</title>
      <link>https://intelligentartifact.com/posts/legora-tests-agents-without-reading-client-work/</link>
      <pubDate>Mon, 02 Nov 2026 14:54:03 -0800</pubDate>
      <guid>https://intelligentartifact.com/posts/legora-tests-agents-without-reading-client-work/</guid>
      <description>Jacob Lauritzen explains lawyer-built tests, restricted production feedback, and customer-supplied examples for improving legal agents without reading confidential client work.</description>
    </item>
    <item>
      <title>Arca’s agents keep financial work moving between human decisions</title>
      <link>https://intelligentartifact.com/posts/arca-agents-financial-work-human-decisions/</link>
      <pubDate>Sat, 31 Oct 2026 09:05:00 -0700</pubDate>
      <guid>https://intelligentartifact.com/posts/arca-agents-financial-work-human-decisions/</guid>
      <description>Aman Singh explains persistent client memory, model checks, and staff feedback for coordinating financial work while advisors retain final decisions.</description>
    </item>
  </channel>
</rss>
