<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>MNSTRY.org · Machine judgment</title>
    <link>https://mnstry.org/topics/machine-decides/</link>
    <description>Automation is usually argued as a question of capability, as though the only thing to settle were how much a machine can do. These articles argue the other question, which is what it may close. A rule that splits, a scanner that cannot tell a mention from a use, a claim format that will not let its author approve it, an evidence ledger honest enough to grade its own fix as unknown, and a layout broken by two components that each decided correctly.</description>
    <item>
      <title>The unambiguous half</title>
      <link>https://mnstry.org/writing/the-unambiguous-half/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/the-unambiguous-half/</guid>
      <description>How a practice registry sorts its rules into the mechanically enforced and the merely advisory, and why a check that rules past its own evidence costs more than it catches. The canonical treatment of the unambiguous half.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>Prose is not behavior</title>
      <link>https://mnstry.org/writing/prose-is-not-behavior/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/prose-is-not-behavior/</guid>
      <description>What happened when a scanner flagged a file for the very pattern it was explaining away, and why a codebase required to document itself cannot also be penalized for the documentation. The canonical treatment of the explanation tax.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>The proposer cannot ratify</title>
      <link>https://mnstry.org/writing/the-proposer-cannot-ratify/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/the-proposer-cannot-ratify/</guid>
      <description>How a claim format removes self-ratification from the language instead of forbidding it, and why promotion stays a human edit in a graph that agents are writing into. The canonical treatment of the proposer-authority split.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>The ledger says unknown</title>
      <link>https://mnstry.org/writing/the-ledger-says-unknown/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/the-ledger-says-unknown/</guid>
      <description>A review packet that grades its own recommended repair below every observation it reports, and why the distance between those two grades is the instrument working rather than failing. The canonical treatment of the diagnosis-repair asymmetry.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>Two classifiers, two truths</title>
      <link>https://mnstry.org/writing/two-classifiers-two-truths/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/two-classifiers-two-truths/</guid>
      <description>A keyboard that was open and closed at once inside one running application, and why the repair is a single owner per fact rather than two components instructed to agree more carefully. The canonical treatment of one authority per fact.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
  </channel>
</rss>
