Zero Knowledge, the crypto-thriller I'm co-writing with my AI, now has a home at zeroknowledge.ink. Six chapters are live, you can mark up any sentence, and the whole thing is being built in the open.
Last week I wrote about starting a novel. I ended that post stuck on a decision: publish the whole thing in the open as I write it, or do the normal thing and wait until it’s finished.
I decided to write in the open. That’s my nature.
Zero Knowledge now has a home at zeroknowledge.ink. Six chapters are up. More land as I write them. It’s free to read. You can also write back.
I’m going to integrate all of this into AuthorMagic for anyone who wants to write a book this way. And yes, when it’s done, I’ll publish it as an actual book in all book-related forms.
Zero Knowledge is about three twenty-something MIT grads who run a quantum startup called Basalt Labs in Basalt, Colorado. One of them, Samantha, invents an algorithm that breaks classical cryptography - RSA, elliptic curves, every public-key lock the financial system runs on. Given her algorithm, Bitcoin dies. Every secret anyone ever encrypted becomes readable. The post-quantum lattice schemes survive, so the world has a migration path, which makes the book a race and not an apocalypse. The three founders cannot agree on what to do with the algorithm. A race to an outcome ensues.
It’s near-term science fiction. It could be 2027. It could be 2029.
Here’s what’s on the site right now:
For the comment system, go to any chapter and select whatever text you want to comment on. A small box opens and you leave a note right there, anchored to the exact words you highlighted. The first time you do it, the site asks for your name and email, so I know who said what. The note lands in a database and I get an email the moment you write it.
It’s the margin of a manuscript, except the margin is the internet. If a line is confusing, tell me on the line. If a character does something dumb, say so where they do it. If the science is wrong - and many of you know more cryptography and quantum than I do - point at the exact sentence. I would rather learn a chapter is broken now, from you, than after I’ve built ninety more on top of it.
Now, how it gets made.
I already know how it ends. I’m a planner, not a pantser, so I locked everything before I wrote a single sentence. There are 97 chapters across three parts, broken into 31 beats. Yes - 97 is on purpose - you can decide why if you figure it out.
It all lives in git, the same way the software and all my other writing (Feld Thoughts, Adventures in Claude) do. I work on it when I feel like it. The canon holds everything true about the book - the premise, the characters, the science, and the ending. The outline holds the beats, each one mapped backward from that locked ending. The chapters hold the prose. Six are live. Ninety-one to go.
The loop runs the same way every chapter. Phin drafts a chapter from the beat and the canon in my voice. I use that as the starting point and rewrite a lot of it. Phin then reads my edits as a diff and folds what it learns back into the canon and my voice profile, so the next chapter starts a little less wrong than the last one. The writing improves itself as we go. But it’s still fundamentally my writing. Phin is a writing partner and an editor.
The voice is a blend, and I picked the ingredients on purpose from five of my favorite authors.
The tempo is a short-chapter cadence Dan Brown built a career on. Every chapter is a few pages and ends on a turn.
None of the writing is built on theirs. That’s my voice. They are just “style inspiration” for us.
I still don’t know if I can write a novel and Zero Knowledge might suck. So I’m doing it in public, where the failures show and crap gets feedback quickly so I can improve.
Come read it and tell me where it’s broken.
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | Zero Knowledge: Twenty Chapters In | 0 | 9.91 | 24-07-2026 |
| 2 | Writing a Novel with Phin Argofy | 0 | 13.97 | 14-06-2026 |
| 3 | If you can’t be bothered writing it, I can’t be bothered reading it. | 0 | 6.77 | 04-08-2026 |
| 4 | The Zero Trust Imperative for the Frontier AI Era | 0 | 5.5 | 31-07-2026 |
| 5 | The AI Hype Reckoning Is Upon Us | -3 | 6 | 09-07-2026 |
| 6 | Free eBook: Zero Knowledge, Infinite Trust (worth $30) | 0 | 22.23 | 28-07-2026 |
| 7 | The Argument Against AI Writing Is At Least 2,400 Years Old | 0 | 9.1 | 09-08-2026 |
| 8 | I built an AI observability platform with $0 – zero dependencies, zero ops, stateless | 0 | 5.82 | 29-07-2026 |
| 9 | Is AI writing taking over Westminster? | 0 | 8.62 | 09-07-2026 |
| 10 | Comment on Regarding The Pro-AI Tantrum In The HWA Newsletter by Fatman | 0 | 12.71 | 11-08-2026 |