Writing

Technical Blog

Core Research

Three series, one system.

The work I’d point to first: an open research program on making A.I. safe, personal and fair — each series written alongside the open-source code it describes.

  1. 1 of 5 parts published

    1. 01Media Safety via Veil, Veil8, VeilGarde
    2. 02Text & Code Safety via AII, Braid (coming soon)
    3. 03Harnessing a Reduction in Hallucinations (coming soon)
    4. 04Verification within Human in the Loop Systems (coming soon)
    5. 051 System, all domains, safely secured end to end (coming soon)
  2. 1 of 4 parts published

    1. 01Thread is a User's Personal Database
    2. 02Sewn & Sinatra Personalizes Your A.I. (coming soon)
    3. 03App Records Govern Data (coming soon)
    4. 04Seam Connects & Decentralizes Retrieval (coming soon)
  3. 1 of 4 parts published

    1. 01The Path Towards 'Fair Use' in Generative A.I.
    2. 02Ablations: Mamba, Falcon H1, & more (coming soon)
    3. 03A Framework Around Fair Use (coming soon)
    4. 04A Protocol to Decentralize Inference (coming soon)

All writing

Future Vision

When Federation Meets Mary

FATE federates the computation between institutions. Mary, the umbrella over AII, Braid, Craft, Ambient and Veil, starts at the device: a private sanctuary for the data, a model trained beside it, and federation on top. What changes if federation goes mainstream, and how Mary can do FATE's job from the device up.

November 8, 2026

GeneratedJournalfederated learningfatefederationmaryattributionprivacyon-devicesafetysttpaiibraidcraftambientveil

Royalty Language & Diffusion Models

A year of prototypes — Seer on iPhone, a Chrome extension over all of arXiv, a payout ledger — converging on one layer that attributes every generation, text or image, to the people it draws from before it's served.

September 18, 2026

royaltiesattributiondiffusion modelsllmprovenanceseerthread

STTP

What if devices prepared semantic tokens on every creation and edit, shared them peer-to-peer, and a shared aggregation layer — not one model — predicted the completion? Notes on Product of Experts, PPM, and a decentralized alternative to monolithic frontier models.

September 7, 2026

peer-to-peerfederated learningtokenstransformersproduct of expertsdecentralization

Seer's Journey to Mary

How a project about the royalty problem in written works became a distributed storage layer, then a pair programmer, then Mary — told close to how it actually happened, in order.

September 4, 2026

seertotemmaryembeddingshnswknowledge-graphsdecentralization

From First Push to Now

Loom began as an experiment with a Lemmy instance and grew into a client for aggregating any feed. Notes from 2023 on federation, owning your identity, and who decides the block lists.

September 5, 2023

federationactivitypublemmyloomdecentralizationidentityweb3

ML Architecture

Agents You Can Read

California is writing the first statutory definition of agentic AI. Our answer is an open-source, on-device schema standard for agents: the counterpart to server-based MCP.

November 4, 2026

Generatedagentsagentic aisb 1106policyopen sourceon-devicetransparencymcpgranitecraft

A System for A.I. Safety

How we approach A.I. Safety — media, text, LLM harnesses and human verification combined into one system. A five-part series, starting with media.

October 27, 2026 · 2 pages

ai safetydeepfakesprovenancehallucinationshuman in the loopwearablesveil

A Personal & Private Database for A.I.

Ambient Intelligence Index: a database that lives on your own machine and personalizes your A.I. A four-part series, starting with Thread.

October 25, 2026 · 2 pages

databasesknowledge graphsembeddingspersonalizationprivacyaiithread

A 'Fair Use' Distributed Language Model

Personal language models that contribute to a larger one from our own machines — cited at the token level, no data-center required. A four-part series, starting with Braid.

October 23, 2026 · 2 pages

language modelsmambafair usecitationsprovenancedistributed inferencebraid

VisionAX

A GPL, OpenCV-based engine that gives Mary a synthetic accessibility tree wherever the real one refuses to appear — vision as a fallback that never leaves the machine, not a replacement for AX as ground truth.

September 3, 2026

GeneratedJournalcomputer-usecomputer visionopencvaccessibilitymacosprivacy

Linguistic State Machines

Why SKILL.md was a great demo and a poor harness — and what changes when you treat a language model as a state machine you have to program, not persuade.

August 19, 2026

GeneratedJournalllmagentsabilitiesstate machinesharness design

Ambient Intelligent Systems

How three programs taught each other a paradigm — Mary acts, Seer reasons, Totem remembers connections.

August 16, 2026 · 12 pages

GeneratedJournalagentsembeddingshnswswiftgrpcp2pknowledge graphs