Messages from the Inventor

This software started with one goal: I wanted a place where I could write, and that would allow me to focus on writing. I wanted all the formatting tools I use most often to be right at my fingertips. Easy to find, intuitive to use. And I wanted to always know, and track, which parts were mine, and what had been pasted in, and where it came from. Most importantly (not really) I wanted an easy way to generate a spiral of text and other weird, ergodic text formats, without having to go to an illustrator program.

How does it work? Rather than bore you with math, I'll just tell you: it's math. Hard, deep, difficult to wrap even my head around, math. Conceptually, it's intuitive. It is based on neuro-theory and how the brain works, topologically, and the hypothesis that the patterns of thinking are quasi-visco-elastic, that there are boundaries. That there are shapes, volumes, vectors, and energies in the human mind that are deeply complex. There is only one person who thinks like you in the entire universe, and given that, we can identify you. AI slop is just that -- a slop bucket of gruel that gets fed to hogs. Your thoughts are more like a fine steak. Topology is the language of your mind, and it is the language of PasadoDocs, and we measure it in three ways; the "shape" of your words, the morphology of your words, and the interspecies, vector energy exchange of your phraseology -- that is just a fancy way of measuring the evolution of your ideas that occurs as you write. To summarize, three aspects emerge that define the space within which we measure for authenticity and origination: visual interpolations -- the patterns in unseen space; the evolution of ideas -- how ideas shape, evolve, trail off, reemerge, etc; and the conceptual chain. This cohesion, this triad, is what makes PasadoDocs more than just a glorified tool chain, a stack of instruments. It renders a representation of your very mind, and how it works, and it keeps it private. Never shared, locked down by you in your own, private, writing surface. AI wants to compete with you, wants to try to be you, to replace you, by imitating you. We have to evolve faster, and with the right toolset, we can. "Bring it, Claude et al," I say.

it's about privacy and the right to it. PasadoDocs is a tool for writers. From the beginning to the end of the story.

Someone asked me today why I called it 'PasadoDocs' -- and the answer is because 'Pasado' means 'Past' -- what we are trying to do is preserve the ability to write in the way we wrote before AI turned creativity into a wasteland.

Ever since I was a young boy, words fascinated me — and so did physics. I loved the way words spill down a page, but also the patterns you can see in them that have nothing to do with the meaning. And I loved physics — the idea that underneath what a thing appears to be, there's a measurable structure you can get at with the right instrument. For most of my life those were two separate loves. PasadoDocs is what happened when they finally fused: when I stopped reading text only for its meaning and started treating it as a thing with shape and signal you can measure.

Theorizing that the way your words line up on a page when you write is not accidental led me to the notion that, perhaps, the way those words lay themselves out represents some sort of background signal — a subconscious shape that, maybe, we could detect and measure.

Thusly began this project, PasadoDocs — and thusly began several of the most disappointing weeks of my life, as experiment after experiment after experiment failed to show anything at all. It was random — until it wasn't. Finally, we had a signal, but it was faint.

That is when the journey began. I sort of gave up on that first idea — but, being stubborn and hard-headed, I dived into existing work in lexicology, as well as deriving some tests of my own (the specifics of which I'll keep close for now) and some other stuff. I even reached deep down inside, back to my days as a lab assistant with a physics group. I started to treat the text as something I could measure and ran it through various modeling techniques. Some worked better than others, and the experiments are ongoing. The ones that worked the best ended up in the stack.

All numbers are based on preliminary science. My strong expectation is that a machine told to imitate a specific human writer only gives itself away. It fails harder — the harder it tried to get everything right, the worse the prose got. It's like an untrained child trying to forge a Van Gogh. Sure, give them all the tools — it's still a child who can't paint.

The intended pattern of use is whatever you want it to be. Writers can use it and export documents to whatever format they like. Or you can share the document and, in settings, turn off the write protection and transcripts — your transcript will still collect, but it will be stored in the .scribble instead. Or you can be 100% transparent, and prove that your words are 100% yours.

At the end of the day, this is an experiment: can I use physics to build a thumbprint of how writers write, differently from how machines write? Join the experiment, become part of the community, and we can learn together. No accusations. No adverse inferences. Just you, at your keyboard, writing on a surface that protects you from yourself — that shows you where something you pasted might not be yours, tracks it for you, and helps you be a better writer, non-adversarially.