<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #codegen</title>
    <link>/tags/codegen/</link>
    <description>Recent bookmarks tagged #codegen</description>
    <lastBuildDate>Mon, 02 Nov 2026 08:24:45 +0000</lastBuildDate>
    <item>
      <title>Introducing Flint - Recursive</title>
      <link>https://recursive.com/updates/introducing-recursive-flint</link>
      <description>We’re introducing Recursive Flint, a mixture-of-experts (MoE) model built for fast agentic coding on local hardware. Flint has 40 billion total parameters and activates just 2.5 billion per token. Our small team of people and agents built it from scratch in under four months.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #flint #llms&lt;/p&gt;</description>
      <pubDate>Fri, 23 Oct 2026 16:55:33 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38820</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>flint</category>
      <category>llms</category>
    </item>
    <item>
      <title>a new model for open source: closed to pull requests, open to remix.</title>
      <link>https://ghuntley.com/remix/</link>
      <description>For what&#39;s the point of reading a pull request that&#39;s been generated by code? All I want is to read and understand the core idea. If it&#39;s a good idea, I might incorporate it back upstream, but there should be no expectation that I will.&#xA;&#xA;You see, open source software is open source by definition because the license says that it&#39;s as is, and that as is permits you to remix software.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #llms #opensource #oss&lt;/p&gt;</description>
      <pubDate>Thu, 15 Oct 2026 00:42:33 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38809</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <category>opensource</category>
      <category>oss</category>
      <enclosure url="https://links.lmorchard.com/static/54fee01a909c2ce14c87ecd89ce85444.jpg" type="image/jpeg"></enclosure>
    </item>
    <item>
      <title>What a year — Massively Parallel Procrastination</title>
      <link>https://blog.fsck.com/2026/10/09/what-a-year/</link>
      <description>For 40 years, writing code was a huge part of my life.&#xA;&#xA;Right up until October 9th, 2025.&#xA;&#xA;One year ago today.&#xA;&#xA;That was the last time I wrote a line of code.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #llms&lt;/p&gt;</description>
      <pubDate>Tue, 13 Oct 2026 23:53:57 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38807</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <enclosure url="https://links.lmorchard.com/static/9b4d0dc3a74ed21bdeec884618eaa543.jpg" type="image/jpeg"></enclosure>
    </item>
    <item>
      <title>telepath-computer/television: The missing GUI for personal agents. Television gives you and your agent a visual space for creating and working with artifacts.</title>
      <link>https://github.com/telepath-computer/television</link>
      <description>Television is the missing GUI for your personal agent. It gives you a visual space for creating and working with artifacts in collaboration with your agent. It works with any agent and any model.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #llms #television&lt;/p&gt;</description>
      <pubDate>Wed, 07 Oct 2026 05:42:28 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38792</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <category>television</category>
      <enclosure url="https://links.lmorchard.com/static/4261389bf3d19a2bed85198f55086c13.png" type="image/png"></enclosure>
    </item>
    <item>
      <title>Wireburst: RSS feeds in Discord, because email is the devil – Cruftbox: My Box of Cruft</title>
      <link>https://cruftbox.com/2026/06/30/wireburst-rss-feeds-in-discord-because-email-is-the-devil/</link>
      <description>The idea is simple. You point Wireburst at your RSS feeds, tell it what category they belong to, and it creates a Discord channel for each feed nested under a category group. New items show up individually. No algorithm. Just a channel you can glance at when you feel like it and ignore when you don’t.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #codegen #discord #llms #nifty #rss&lt;/p&gt;</description>
      <pubDate>Wed, 07 Oct 2026 02:36:05 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38789</guid>
      <category>codegen</category>
      <category>discord</category>
      <category>llms</category>
      <category>nifty</category>
      <category>rss</category>
      <enclosure url="https://links.lmorchard.com/static/1b38f7dd761cfde1bfb43c89cd9fe20b.jpg" type="image/jpeg"></enclosure>
    </item>
    <item>
      <title>AI Didn’t Make Programming Easier. It Just Made It Differently Difficult – Communications of the ACM</title>
      <link>https://cacm.acm.org/opinion/ai-didnt-make-programming-easier-it-just-made-it-differently-difficult/</link>
      <description>AI does not, therefore, diminish the craft; it widens it, deepens it, and makes more of the work explicitly intellectual. The work becomes differently difficult because it demands more sophisticated forms of expertise: judgment over recall, architecture over syntax, orchestration over implementation. These are not easier skills to develop or demonstrate, they are simply different ones, and perhaps ultimately more demanding.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #llms #work&lt;/p&gt;</description>
      <pubDate>Tue, 29 Sep 2026 16:03:15 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38775</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <category>work</category>
    </item>
    <item>
      <title>Thorsten Ball - What I believe about the future of software development</title>
      <link>https://thorstenball.com/blog/2026/09/19/what-i-believe-about-the-future-of-software-development/</link>
      <description>This was originally posted on X and blew up. To plant my flag, to say that these are things I believed in September 2026, here it is on the blog, non-ephemeral. Some of these predictions are just observations, they’ve long been true at companies like Amp. Others will take some time to play out.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #future #llms #work&lt;/p&gt;</description>
      <pubDate>Mon, 28 Sep 2026 05:57:31 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38774</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>future</category>
      <category>llms</category>
      <category>work</category>
    </item>
    <item>
      <title>I don&#39;t like LLMs</title>
      <link>https://martinfowler.com/articles/2026-dont-like-llms.html</link>
      <description>One of my most successful life-hacks is to avoid people I don’t like or don’t trust. I decline to interact with them socially, and make a deliberate effort to avoid working with them too, even if they are doing much that is beneficial. I feel that hanging out with pleasant, capable people, the people with integrity, has made my life a far better one. Hence my visceral dislike of interacting with an LLM that’s not just making a pretense of being human, but also posing as the kind of human I walk away from.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #agents #ai #codegen #llms&lt;/p&gt;</description>
      <pubDate>Mon, 21 Sep 2026 17:27:05 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38756</guid>
      <category>agents</category>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <enclosure url="https://links.lmorchard.com/static/b594014fc0a384b85085754db7e6020f.png" type="image/png"></enclosure>
    </item>
    <item>
      <title>The Wind, The Wind | blarg</title>
      <link>https://exple.tive.org/blarg/2026/09/10/the-wind-the-wind/</link>
      <description>It looks like people are starting to come around about designing, planning and building houses by counting number of nails they used. It’s probably for the best; people sure went crazy about it for a year or two, though.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #llms #work&lt;/p&gt;</description>
      <pubDate>Thu, 10 Sep 2026 23:54:03 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38748</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <category>work</category>
    </item>
    <item>
      <title>Engineers grieve a job that no longer exists - LeadDev</title>
      <link>https://leaddev.com/career-development/engineers-grieve-a-job-that-no-longer-exists?utm_source=ActiveCampaign&amp;utm_medium=email&amp;utm_content=Engineers%20are%20grieving&amp;utm_campaign=Originals%3A%20%20Issue%20312%20%2827%20August%202026%29%20%28Copy%29</link>
      <description>The more AI-generated code a team produces, the more review work lands on the engineers who care most about quality, often the most experienced people on the team. The volume of output rises while the nature of the work shifts from creation to inspection, and the engineers doing the hardest cognitive labor appear, by the metrics, to be less productive than the ones generating code with AI.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #career #codegen #work&lt;/p&gt;</description>
      <pubDate>Thu, 10 Sep 2026 18:25:38 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38744</guid>
      <category>ai</category>
      <category>career</category>
      <category>codegen</category>
      <category>work</category>
      <enclosure url="https://links.lmorchard.com/static/a2d3a064d8c0e7890ed87c9b3a18bff4.jpg" type="image/jpeg"></enclosure>
    </item>
    <item>
      <title>AI-Written Code Is Still Your Code. Are You OK With That?</title>
      <link>https://martiansoftware.com/articles/ai-written-code-is-still-yours</link>
      <description>But when you build software, you own it, and I don’t only mean in the intellectual property sense. You also take on the responsibility for its quality and its security, and for debugging, operating, maintaining, and evolving it over time. Are you prepared for that when building software with AI? That’s the new question: not “Can we build this?” but rather “Do we want to own this?” It should at least be a conscious decision rather than a responsibility you discover after the code is already yours.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #llms&lt;/p&gt;</description>
      <pubDate>Tue, 01 Sep 2026 14:12:32 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38726</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
    </item>
    <item>
      <title>Vibecoding isn&#39;t as fun as writing code by hand — The Autodidacts</title>
      <link>https://www.autodidacts.io/vibecoding-isnt-as-fun-as-writing-code-by-hand/</link>
      <description>Vibecoding is like being an executive of a large company that is barely under your control. You never feel like you really know what’s going on, and there’s always the suspicion of sabotage and loafing. Things appear fully formed, but not quite how you imagined. Sometimes they work, and sometimes they don’t, and there’s nothing you can do about it, other than pouring more money into the black box, and yelling louder. So that’s what you do.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #codegen #llms #vibecoding&lt;/p&gt;</description>
      <pubDate>Sat, 22 Aug 2026 04:37:49 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38698</guid>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <category>vibecoding</category>
    </item>
    <item>
      <title>Why shaming people about AI slop isn’t enough to stop Big AI - Anil Dash</title>
      <link>https://www.anildash.com/2026/08/21/ai-slop-and-shame/</link>
      <description>This is the kind of solution that most AI critics are not allowing for right now when they only picture a shame-based corrective to individual people’s use of AI. It is possible to build human-centric, empowering tools and platforms that are owned by the people instead of by billionaire tycoons, that are responsible about the environment and with people’s data and privacy, that are accountable to the communities that they serve. If we engaged every person who made some AI slop and said, “would you rather have tools that help you make something amazing, and brought you into a community of creators?” I don’t think anybody would say no.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #agents #ai #codegen #llms&lt;/p&gt;</description>
      <pubDate>Fri, 21 Aug 2026 21:14:20 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38697</guid>
      <category>agents</category>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <enclosure url="https://links.lmorchard.com/static/91929c68d2b0a6934ec4fdfba6f2b9d1.jpg" type="image/jpeg"></enclosure>
    </item>
    <item>
      <title>openai/symphony: Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.</title>
      <link>https://github.com/openai/symphony</link>
      <description>Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #agents #codegen #llms #openai&lt;/p&gt;</description>
      <pubDate>Tue, 18 Aug 2026 17:56:42 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38691</guid>
      <category>agents</category>
      <category>codegen</category>
      <category>llms</category>
      <category>openai</category>
      <enclosure url="https://links.lmorchard.com/static/ddfc97416900b14fa9684e571fbc4e1f.png" type="image/png"></enclosure>
    </item>
    <item>
      <title>Astro&#39;s GitHub issue backlog is heading to zero for the first time in 5 years. Now Cloudflare is open-sourcing the tool that did it. - The New Stack</title>
      <link>https://thenewstack.io/cloudflare-astro-triage-bot/</link>
      <description>6 months after Cloudflare acquired the team behind Astro, co-founder Fred Schott explains how an AI agent is emptying the project&#39;s issue tracker -- and why the hardest part is still left to a human&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #agents #ai #codegen #llms&lt;/p&gt;</description>
      <pubDate>Mon, 10 Aug 2026 17:12:43 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38675</guid>
      <category>agents</category>
      <category>ai</category>
      <category>codegen</category>
      <category>llms</category>
      <enclosure url="https://links.lmorchard.com/static/0b30cc21a665bc4cab1b987b334c50c3.jpg" type="image/jpeg"></enclosure>
    </item>
  </channel>
</rss>
