<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Large language models - News</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Large language models News feed</description>
    <item>
      <title>OpenAI Open-Sources Symphony, a SPEC.md for Autonomous Coding Agent Orchestration</title>
      <link>https://www.infoq.com/news/2026/05/openai-symphony-agents/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/openai-symphony-agents/en/headerimage/openai-symphony-1779047353917.jpg"/&gt;&lt;p&gt;OpenAI Symphony is an agent orchestrator that uses project-management tools, like issue trackers, as a control plan to coordinate multiple coding agents. Instead of developers managing interactive coding sessions, Symphony manages "tasks" by assigning each one to a dedicated agent that works autonomously to completion. Once a task is finished, a human is in charge to review the resulting output.&lt;/p&gt; &lt;i&gt;By Sergio De Simone&lt;/i&gt;</description>
      <category>OpenAI</category>
      <category>Orchestration</category>
      <category>Agents</category>
      <category>Large language models</category>
      <category>Open Source</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Sun, 17 May 2026 20:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/openai-symphony-agents/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</guid>
      <dc:creator>Sergio De Simone</dc:creator>
      <dc:date>2026-05-17T20:00:00Z</dc:date>
      <dc:identifier>/news/2026/05/openai-symphony-agents/en</dc:identifier>
    </item>
    <item>
      <title>Ubuntu Embraces Local AI Instead of Cloud-First OS Integration</title>
      <link>https://www.infoq.com/news/2026/05/ubuntu-on-device-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/ubuntu-on-device-ai/en/headerimage/ubuntu-on-device-ai-1778958515321.jpeg"/&gt;&lt;p&gt;Ubuntu has outlined its AI strategy, describing it as a deliberate departure from industry trends towards cloud-centric, AI-first operating systems. Instead, the company says, Ubuntu will focus future releases on local intelligence, modular design, and strict user control.&lt;/p&gt; &lt;i&gt;By Sergio De Simone&lt;/i&gt;</description>
      <category>Operating Systems</category>
      <category>Linux</category>
      <category>Agents</category>
      <category>Large language models</category>
      <category>DevOps</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Development</category>
      <category>news</category>
      <pubDate>Sat, 16 May 2026 20:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/ubuntu-on-device-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</guid>
      <dc:creator>Sergio De Simone</dc:creator>
      <dc:date>2026-05-16T20:00:00Z</dc:date>
      <dc:identifier>/news/2026/05/ubuntu-on-device-ai/en</dc:identifier>
    </item>
    <item>
      <title>Anthropic Introduces Routines for Claude Code Automation</title>
      <link>https://www.infoq.com/news/2026/05/anthropic-routines-claude/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/anthropic-routines-claude/en/headerimage/generatedHeaderImage-1778774115333.jpg"/&gt;&lt;p&gt;Anthropic has introduced a new feature called Routines for Claude Code, allowing developers to configure automated coding workflows that run on schedules, through API calls, or in response to external events.&lt;/p&gt; &lt;i&gt;By Daniel Dominguez&lt;/i&gt;</description>
      <category>OpenAI</category>
      <category>AI Coding</category>
      <category>Anthropic</category>
      <category>Software Development</category>
      <category>Claude</category>
      <category>github</category>
      <category>Artificial Intelligence</category>
      <category>Large language models</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Fri, 15 May 2026 15:51:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/anthropic-routines-claude/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</guid>
      <dc:creator>Daniel Dominguez</dc:creator>
      <dc:date>2026-05-15T15:51:00Z</dc:date>
      <dc:identifier>/news/2026/05/anthropic-routines-claude/en</dc:identifier>
    </item>
    <item>
      <title>Anthropic Traces Six Weeks of Claude Code Quality Complaints to Three Overlapping Product Changes</title>
      <link>https://www.infoq.com/news/2026/05/anthropic-claude-code-postmortem/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/anthropic-claude-code-postmortem/en/headerimage/generatedHeaderImage-1778491231246.jpg"/&gt;&lt;p&gt;Anthropic published a postmortem tracing six weeks of Claude Code quality complaints to three overlapping product-layer changes: a reasoning effort downgrade, a caching bug that progressively erased the model's own thinking, and a system prompt verbosity limit that caused a 3% quality drop. The API and model weights were unaffected. All issues were resolved April 20.&lt;/p&gt; &lt;i&gt;By Steef-Jan Wiggers&lt;/i&gt;</description>
      <category>Generative AI</category>
      <category>Anthropic</category>
      <category>AI Architecture</category>
      <category>Large language models</category>
      <category>Code Quality</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Development</category>
      <category>news</category>
      <pubDate>Thu, 14 May 2026 09:16:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/anthropic-claude-code-postmortem/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</guid>
      <dc:creator>Steef-Jan Wiggers</dc:creator>
      <dc:date>2026-05-14T09:16:00Z</dc:date>
      <dc:identifier>/news/2026/05/anthropic-claude-code-postmortem/en</dc:identifier>
    </item>
    <item>
      <title>Anthropic Launches Claude Platform on AWS</title>
      <link>https://www.infoq.com/news/2026/05/anthropic-claude-aws/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/anthropic-claude-aws/en/headerimage/generatedHeaderImage-1778682420283.jpg"/&gt;&lt;p&gt;Anthropic has announced the general availability of Claude Platform on AWS, a new deployment option that gives AWS customers direct access to Anthropic’s native Claude platform using AWS authentication, billing, and monitoring services.&lt;/p&gt; &lt;i&gt;By Daniel Dominguez&lt;/i&gt;</description>
      <category>Anthropic</category>
      <category>AWS</category>
      <category>Software Development</category>
      <category>Claude</category>
      <category>Cloud Computing</category>
      <category>Artificial Intelligence</category>
      <category>Large language models</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Wed, 13 May 2026 19:20:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/anthropic-claude-aws/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</guid>
      <dc:creator>Daniel Dominguez</dc:creator>
      <dc:date>2026-05-13T19:20:00Z</dc:date>
      <dc:identifier>/news/2026/05/anthropic-claude-aws/en</dc:identifier>
    </item>
    <item>
      <title>Coder Agents Enable Running AI Coding Workflows on Self-Hosted Infrastructure</title>
      <link>https://www.infoq.com/news/2026/05/coder-agents-self-hosted-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/coder-agents-self-hosted-ai/en/headerimage/coder-agents-self-hosted-ai-1778516884639.jpeg"/&gt;&lt;p&gt;Coder Agents is a model-agnostic platform designed to let organizations run AI coding agents on their own infrastructure, rather than relying on cloud-based services. This allows teams to maintain full control over code, data, and execution environments.&lt;/p&gt; &lt;i&gt;By Sergio De Simone&lt;/i&gt;</description>
      <category>AI Coding</category>
      <category>Agents</category>
      <category>Large language models</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Mon, 11 May 2026 17:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/coder-agents-self-hosted-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Large+language+models-news</guid>
      <dc:creator>Sergio De Simone</dc:creator>
      <dc:date>2026-05-11T17:00:00Z</dc:date>
      <dc:identifier>/news/2026/05/coder-agents-self-hosted-ai/en</dc:identifier>
    </item>
  </channel>
</rss>
