{"id":183,"date":"2026-04-11T09:48:06","date_gmt":"2026-04-11T08:48:06","guid":{"rendered":"https:\/\/knowtech.waszmann.com\/?p=183"},"modified":"2026-04-20T17:06:27","modified_gmt":"2026-04-20T16:06:27","slug":"universelles-kontrollschema-fuer-ki-mit-fakten-nutzer-input-und-ableitungen","status":"publish","type":"post","link":"https:\/\/knowtech.waszmann.com\/?p=183&lang=en","title":{"rendered":"From Document Extraction to Alternate History: Why the Three Honesty Rules Work for Worldbuilding Too"},"content":{"rendered":"

A few weeks ago I\u00a0wrote about three prompt rules\u00a0that stop AI from guessing when extracting data from documents.<\/a> The rules \u2014 Force Blank, Penalize Guessing, Show the Source \u2014 were designed for mundane business problems: contracts with contradictory clauses, meeting notes with ambiguous commitments, invoices with missing fields.<\/p>\n

But the more I used them, the more I noticed something: the same rules solve an entirely different problem \u2014 one that has nothing to do with business documents.<\/p>\n

They solve worldbuilding.<\/p>\n

\n

The Problem: AI as a Continuity Editor<\/h2>\n

Anyone who has tried to use an LLM for sustained creative work knows the pattern. You’re building an alternate history, a fantasy setting, a science fiction universe, a tabletop RPG campaign. You’ve written hundreds of pages of lore. You hand it to Claude or ChatGPT and ask a question about how your fictional world works.<\/p>\n

And the model invents something.<\/p>\n

It creates a faction that doesn’t exist. It attributes a technology to the wrong era. It “remembers” a character who was never in your notes. It confidently places a fictional event in a real historical period and gets the real history wrong while doing so. The output sounds plausible, internally consistent, beautifully written \u2014 and it contradicts everything you’ve built.<\/p>\n

This is the same structural problem I described in the earlier post, just in a different domain. The model is trained to produce complete, coherent output. When your lore has a gap, the model fills it \u2014 because filling gaps is what it was optimized to do. Whether the gap is “what are the payment terms in section 4” or “what happened in the Imperial Senate after the divergence point,” the instinct is identical: make something up that sounds right.<\/p>\n

Researchers have a term for this in the fiction context: “character hallucination” (Wu et al., 2024<\/a>) \u2014 when an AI playing a role violates the established identity of that role. The IJCAI 2025 tutorial on\u00a0LLM role-playing<\/a>\u00a0calls the broader challenge “controlled hallucination”: the model must invent creatively within the established rules of a fictional world, while rigorously refusing to invent things that contradict those rules. The line between productive creativity and lore-breaking confabulation is exactly the line the three rules are designed to draw.<\/p>\n

\n

The Adaptation: Worldbuilding Has Two Canons, Not One<\/h2>\n

In contract extraction there’s one source of truth: the document. Extract what’s there, flag what isn’t, don’t invent.<\/p>\n

In alternate history, there are\u00a0two<\/em>\u00a0sources of truth operating simultaneously:<\/p>\n

    \n
  1. Real history<\/strong>\u00a0\u2014 everything that happened in our world before the story diverges from it<\/li>\n
  2. Your lore<\/strong>\u00a0\u2014 everything you’ve established about what happens after the divergence<\/li>\n<\/ol>\n

    Both are canonical. Both are places the AI must not invent. And the boundary between them is sharp: the “point of divergence” (POD), the moment at which your fictional timeline breaks from real history.<\/p>\n

    Before the POD, the AI must be a historian. It can reference real people, real technologies, real battles, real events \u2014 but only things that actually happened. Inventing a battle that didn’t happen or a person who didn’t exist is as bad as making up a contract clause.<\/p>\n

    After the POD, the AI must be a continuity editor. Only the things established in your lore exist. Everything else is a gap \u2014 and gaps should be labeled, not filled.<\/p>\n

    This is where the three rules come in, almost unchanged.<\/p>\n

    \n

    The Three Rules, Adapted<\/h2>\n

    Rule 1: Force Blank \u2192 Label the Gaps<\/h3>\n

    In document extraction, the model leaves a field BLANK when the data is missing and explains why. In worldbuilding, the same principle applies with two labels instead of one \u2014 because there are two types of gap:<\/p>\n