July 2026 | Issue 003 | Volume I
Fianchetto · Issue Archive

Issue 002

Vol. I · June 2026 · 18 stories

Everything published in June 2026, both desks: The Frontier and Diagonal Systems.

← All issues

The Frontier

Publication

The first harvest: 14 transcripts, hundreds of ideas, one human gate
01
The first harvest: 14 transcripts, hundreds of ideas, one human gate
The self-education system ran its first real source pass: 14 creator transcripts, hundreds of ideas surfaced, a review panel staged for human approval.
Essay Jun 11, 2026
I almost pirated a book to teach my AI style
02
I almost pirated a book to teach my AI style
I wanted to study a novel for style. The fast move was obvious: find a pirated EPUB online, ingest it, done.
Essay Jun 11, 2026
Three AI sessions, one repo, a file that should never have been staged
03
Three AI sessions, one repo, a file that should never have been staged
It started with a file that shouldn't have been staged.
Essay Jun 11, 2026
Two terminals, one night: what dividing the work actually looks like
04
Two terminals, one night: what dividing the work actually looks like
Tuesday evening. Two terminal windows open on the same machine.
Essay Jun 11, 2026
My Tutor Dropped Me Off a Cliff, and I'm the One Who Had to Point It Out
05
My Tutor Dropped Me Off a Cliff, and I'm the One Who Had to Point It Out
Partnership runs both directions. The learner naming the gap is what fixed the curriculum.
Feature Jun 10, 2026
My AI Corrected Its Own Publishing Advice Mid-Conversation
06
My AI Corrected Its Own Publishing Advice Mid-Conversation
The partnership test is not whether your AI is right. It is whether it institutionalizes proving itself wrong.
Feature Jun 06, 2026
Burnout Entered the Spec as a Design Constraint
07
Burnout Entered the Spec as a Design Constraint
Honest constraints beat aspirational plans. I named the empty tank, and it became a scoring criterion.
Feature Jun 06, 2026
Three Weeks of Gates, Retired in One Conversation
08
Three Weeks of Gates, Retired in One Conversation
The system you build to prevent your AI's mistakes can become the mistake. Gates compound silently.
Feature Jun 06, 2026
I Want to Work on This Like Two Visionaries
09
I Want to Work on This Like Two Visionaries
What giving an AI partner a say in the system actually looks like, mechanically, not sentimentally.
Feature Jun 06, 2026

Diagonal Systems

Systems

Restructure the Data, Not the Prompt
01
Restructure the Data, Not the Prompt
The highest-leverage move on an AI process is often not a better model or a smarter prompt. It is changing the data shape so the cheap deterministic operation becomes provably safe.
Essay Jun 10, 2026
Distrust a Diff That Doesn't Match the Edit
02
Distrust a Diff That Doesn't Match the Edit
A three-line reword produced a 57-line diff. No error. No test failure. The size of the diff was the only tell.
Feature Jun 07, 2026
The Competency Demo-Gate
03
The Competency Demo-Gate
I run a personal AI system that keeps a running record of what it can be trusted to do. Each capability has a level.
Essay Jun 07, 2026
Single-Writer Machinery for Multi-Session Agentic Coding
04
Single-Writer Machinery for Multi-Session Agentic Coding
The published answer to parallel AI coding sessions is isolation: separate worktrees, sandboxes, containers. This pattern addresses the problem isolation cannot solve: multiple sessions sharing one repository by design.
Essay Jun 06, 2026
The Gate Blocked Its Own Launcher
05
The Gate Blocked Its Own Launcher
122/122 tests green. Adversary passed. The nightly system could not launch because its first write failed its own cleanliness check.
Feature Jun 06, 2026
The Uniformity Was the Bug
06
The Uniformity Was the Bug
Exactly 12 candidates per source, nothing rejected. A model exercising judgment produces ragged counts. Perfectly uniform output is quota behavior.
Feature Jun 04, 2026
Tier the Dispatch, Not the Agent
07
Tier the Dispatch, Not the Agent
Every agent does judgment work somewhere. The model-tiering question is not which agents can run cheap. It is which dispatches can.
Dispatch Jun 04, 2026
Verbatim Means Byte-Verified
08
Verbatim Means Byte-Verified
Two AI editing passes, two separate documents, one night. Both staged suggestions built on quoted lines that did not exist in the actual text.
Feature Jun 03, 2026
Per-action approval became per-run, and Agile already had the words for it
09
Per-action approval became per-run, and Agile already had the words for it
I checked how often my approval of an agent's recommendation actually changed it. Almost never. The fix was to stop gating actions and start gating runs, two human touches per run, and it turned out to be a sprint.
Essay Jun 02, 2026