HUMANIZE.md | Research-based AI Writing Humanization Standard
HUMANIZE.MD · {{ currentFile }}
Prompt · Research · Writing standard

Humanize.md

Teaching AI to write like a person, not a press release.

HUMANIZE.MD is a small, open writing standard: one markdown prompt you hand to any language model so its output reads the way people actually write. Plainspoken. Specific. Free of the tics that give machine text away.

It started as a personal correction file, the same notes pasted ahead of every draft, patched so many times it hardened into something closer to a method. The full rulebook lives on Method, and the research it leans on lives on Research.

Pietro Impagliazzo
Author Pietro Impagliazzo {{ email }} Writer & designer behind the HUMANIZE.MD standard.
The method

The rulebook, in full

The rulebook below is the whole method. Not an essay about writing well, not a list of tips: the actual prompt, word for word, that gets pasted ahead of a draft before it goes anywhere.

It grew out of annoyance more than theory. The same corrections kept recurring, so eventually they got written down once instead of retyped for the hundredth time. What follows is organized by the kind of mistake it corrects, not by importance, because in practice they matter about the same amount.

Copy it. Paste it ahead of a prompt. Adjust nothing unless a section clearly doesn't apply to what you're writing.

Before / after, rule by rule
Before

{{ beforeText }}

After

{{ afterText }}

Download
{{ r.title }}

{{ r.body }}

Self-check before output
  1. {{ item }}
The research

Why the rules are the rules

The rulebook isn't a matter of taste. It's built on a review of how synthetic and human writing actually diverge, from word-level predictability up to how a story gets told. What follows is a working summary. The full paper, with sources, is downloadable at the bottom.

{{ s.title }}

{{ s.body }}

Perplexity
Humansurprise per word →AI
Human word choice spreads wide with a long tail; AI clusters on the predictable next word.
Burstiness
Human
AI
Each bar is a sentence. Human swings, AI stays flat.
Parataxis vs hypotaxis
Parataxis
Hypotaxis
Equal clauses chained side by side, versus clauses nested by subordination.
Nouns vs verbs
Human · ~1/4 nouns
AI · ~1/3 nouns
Human writing leans on verbs; AI packs in more nouns.
Semantic vs episodic
Semantic
Episodic
A web of facts, versus one moment actually lived.
Hedged vs committed
AI · hedgedHuman · commits
AI qualifies everything; a person takes a position.
The tell-tale lexicon
AI · same words, in step
Human · varied
AI reaches for the same words in lockstep.
Wall before epiphany
the wallepiphany
Human stories dwell on the wall before the win.
Rules to output
Concrete instructions, made specific enough to follow.

{{ s.title }}

{{ s.body }}

Metric Human writing AI writing (typical)
{{ row.metric }} {{ row.human }} {{ row.ai }}

The gap between machine fluency and human writing keeps narrowing, but the seams are still visible if you know where to look. Closing them isn't about hiding that a tool was used. It's about using it well enough that the writing keeps the friction, the specificity, and the point of view that make it worth reading in the first place.

Download the paper (PDF)
Get in touch

Write to a human

Pietro Impagliazzo
Independent researcher Pietro Impagliazzo {{ email }} Writing and designing HUMANIZE.MD. Reach out about the method, the research, or anything that still reads a little too much like a machine wrote it.
md
HUMANIZE.MD
Markdown Document
md
Reopen HUMANIZE.MD