Editorial
Every article on this site is written with AI assistance. We say so on every byline, and we mean it as a statement of method, not an apology.
The Problem We're Solving
Classical Chinese scholarship has a scale problem. The I-Ching alone has accumulated over two thousand years of commentary, much of it untranslated into English. The Yilin contains 4,096 poetic verses. The Xieji Bianfang Shu runs to thirty-six volumes. The Ten Wings, the Eight Palaces, the Liu Yao method, Qimen Dunjia, Ziwei Doushu, classical physiognomy — each tradition has its own body of source texts, its own interpretive history, its own internal logic.
No single scholar could produce sixty-six articles across all of these traditions at the depth we publish, with trilingual support, in any reasonable timeframe. The work would take years. The traditions deserve better than waiting years.
AI changes the economics. Not the scholarship — the economics.
What the AI Does
The AI (Claude Opus 4.6) drafts text under close editorial direction. It researches across source materials. It produces first drafts that I then read, challenge, restructure, and rewrite. It handles the mechanical work of translation verification, cross-referencing, and consistent formatting across sixty-six articles in three languages.
The AI is fast at things that are slow for humans: synthesising information from multiple classical sources, maintaining consistency across a large body of work, and producing readable prose from technical material. It does these things well enough that I can focus my time on what matters.
What I Do
I decide what to write about. I determine the editorial angle — which source texts to prioritise, which interpretive traditions to follow, which claims to include and which to leave out. I validate the scholarship against classical sources. I read every line before it publishes.
The AI does not know which translation of Hexagram 1 is more faithful to the original. It does not know that the Confucian commentary layer alienates Western readers, or that the Yilin's poetic tradition is underrepresented in English-language scholarship, or that a tarot reader approaching the I-Ching for the first time needs the trigrams explained as characters rather than abstractions. These are editorial judgments. They require years of study, cultural context, and an understanding of who the reader is and what they need.
The AI is a tool. I am the editor. The distinction matters.
Why We're Transparent
Because hiding it would be dishonest, and dishonesty is corrosive to the kind of trust that scholarship requires. If you're reading an article about the hexagram calendar system that Meng Xi and Jing Fang developed in 100 BC, you deserve to know how that article was produced. Not because AI-assisted work is lesser — but because you have the right to evaluate the method.
We think the method stands on its own merits. The articles are well-researched, well-sourced, and carefully edited. The scholarship is sound. The writing is clear. If those things are true, the tool used to produce them is a fact about process, not a mark against quality.
We also think transparency will age well. The EU's AI transparency regulations take effect in August 2026. Google recommends disclosure wherever a reader might wonder “how was this created?” The direction is clear: the standard is moving toward disclosure, not away from it. We'd rather be early than late.
The Toolchain Is Open Source
We don't just disclose the use of AI. We publish the tools.
Inkstone is an open-source set of Claude Code skills built for classical Chinese scholarship. It includes verse explanation (bilingual commentary on classical texts), verse-to-image prompt composition (the pipeline that generates our hero images through fal.ai), UI/UX design review, and i18n SEO tooling. Anyone can inspect it, use it, or improve it.
Publishing the toolchain is the strongest form of transparency we know. It's not enough to say “we used AI.” We show you exactly how, and we give you the tools to do the same.
What This Means for You
If you're reading Six Lines for the scholarship, judge it on the scholarship. The sources are cited. The reasoning is shown. The classical texts are quoted in their original language alongside English translations. If something is wrong, it's wrong regardless of how it was produced — and we want to hear about it.
If you're curious about the process, the About page has a concise summary. Inkstone's repository has the details.
If you think AI-assisted scholarship is illegitimate on principle, we respectfully disagree. The tradition we're studying is three thousand years old. It has survived bronze, bamboo, paper, moveable type, and digital screens. It will survive this too. What matters is whether the work is good.