FM 03SEAN SOOCH
FM 03 · FIELD MANUAL · ELEVEN SYSTEMS, THREE WORLDS, ONE OPERATORCHANGE 3 · SEPTEMBER 2026

Operator's manual for thirteen working systems built at the intersection of all three, by a medical student and military officer using frontier AI as the engineering tool. 150,906 lines across 247 files, every system live, every one measured from your browser as you read this.

↑ hover a world to tint the page · click to filter the systems · press / for the index

DISTRIBUTION STATEMENT A. Approved for public release; distribution is unlimited. Nothing on this page is a mockup. seansooch.dev · Vol. 03 of an edition series, one per model class
Plate 1. Launch film. Vol. 03 in motion: the cover, the topology answering, the roll call, the record, the index.1:20 · sound on
Figure 1-1. Deployment topology. One static origin, eighteen systems, five domains.status: probing from your browser…
reachablewaking (free tier cold start)no responseprobinground trip in milliseconds, measured by an opaque fetch from this tab; it proves the host answers, not that the page is correct
Chapter 1

Purpose and scope

1-1.Purpose

This manual documents five months of learning and building in spare hours. These projects were made possible by tools that lowered the technical barrier between an idea and working software. Others will bring different experience and build better things.

1-2.Scope

Everything listed is deployed and public. Chapter 2 does not take that on faith: when this page loads, your browser pings every host in Figure 1-1 and records what came back. Chapter 3 lists the systems by domain, Chapter 4 collects the written doctrine, Chapter 5 the smaller equipment. Appendix A is the change record for the manual itself.

1-3.Method

Every system was specified by the operator and written with Claude, then verified the way a clinician verifies a lab: against a source, by a second reader, and against the live deployment rather than the local copy. Medical content carries its citations. Scoring tables cite the governing publication. Where a source deck was wrong, the question was corrected and the correction logged.

NOTE

Study tools on this site are for exam preparation and are not medical advice. Clinical calculators and field references are teaching aids; confirm with the governing guideline before use on a patient.

Chapter 2

Readiness

counts recounted 14 Sep 2026 · reachability measured live on every page load

Table 2-1. Portfolio readiness. Static figures are recounted at every edition; live figures come from Table 2-2.

MeasureResultStandard
Lines of code150,906unique source files, generated data excluded; 21,761 of these are one project's test suite
Source files247html, js, css, python, typescript
Board-style questions12,9727 question banks, 8 subjects, every item reviewed at least twice
Players & teams tracked1,106sports intel across 12 data sources
Systems reachable of 17measured from your browser, now
Median round tripmilliseconds, edge-cached static hosts; the one server-rendered app is excluded while it wakes
Months since first deploy5April to September 2026, evenings and weekends

Table 2-2. System status. Same probe as Figure 1-1, in list form.

SystemHostDomainStatusRound trip
CAUTION

The probe is an opaque cross-origin fetch, so it can only report that a host answered, not that the answer was the right page. Cloudflare Pages serves a soft 200 for unknown paths. Treat green as "the lights are on" and click through for anything that matters.

Chapter 3

Systems

thirteen systems, figures 3-1 through 3-13 · each figure is a link
MedicineFig. 3-1

Step 2 CK QbankRebuilt

Public study site over seven Anki-derived banks: 12,972 board-style questions and 12,357 guide facts across eight subjects, a UWorld-style test engine with tutor and exam modes, per-system performance, and three drill tools. Built by a chunk, author, independent-review, adversarial-triage pipeline that caught and corrected about 100 factual errors in the commercial source decks.

12,972 questions8 subjects2-3 review passes LiveOpen →
Medicine · QIFig. 3-2

Patient Handoff Tracker

Full-stack I-PASS/SBAR handoff system built for a real emergency department: Joint Commission compliance metrics, HIPAA-conscious audit logging, role-based access, and a QI dashboard. Flask and SQLite on a free tier, so the first load wakes the server.

20 endpoints7 DB tablesFlask Live · ~30s cold startOpen →
Medicine · CardiologyFig. 3-3

Read This

Pattern-interpretation trainer: 28 procedurally generated rhythms, a fixed 8-step 12-lead read with MI localization by territory, and an outside-in CXR module, all calibrated to 25 mm/s, all sourced.

28 rhythms8 read steps100% sourced LiveOpen →
Medicine × GameFig. 3-4

MICRO TD

Tower defense that enforces the drug-bug matrix: 20 pathogens, 27 antibiotics, resistance evolution on wrong-drug hits, synergy combos, and a Supabase leaderboard. React 19 + Canvas at 60fps.

20 pathogens27 drugs60 fps Live · best on desktopPlay →
MilitaryFig. 3-5

Warrior Ready

All-branch PT command center at 2026 standards: six score calculators, body composition, run pacer with SVG splits, ruck planner, and score history. 52 scoring claims verified against official publications.

6 branches52 claims verified0 deps LiveOpen →
Machines · AI SafetyFig. 3-6

AGI Capability Tracker

Dashboard across 8 capability domains, 25+ frontier models, and dozens of benchmarks: composite AGI score, verified ARC-AGI cells, a capability-milestones timeline, safety scatter plot, automated data pipeline, and a restricted Mythos Mode. Refreshed August 2026.

25+ models8 domains3 milestones LiveOpen →
Machines × MedicineFig. 3-7

Simulators

Four sims, one umbrella: the Alignment Simulator (run a frontier lab, 12 decisions, 6 endings, built from the Risk Stack paper), Code Blue (spacebar CPR with live rate and depth feedback, AHA 2020), Half-Life Tracker (caffeine, hydration, and BAC pharmacokinetics), and Pocket Telescope (live night-sky ID and star quizzes).

4 sims24 decisions11 endings LiveRun →
Sports · Fantasy FootballFig. 3-8

Edge Draft Terminal

Draft intelligence terminal for a 12-team half-PPR league: an 862-player board scored as per-source deviation from consensus ADP, weekly projections priced as points above replacement, Monte Carlo pick-path simulation in a worker, an in-season wire of injuries and market movers, and read-only replay of a live Sleeper draft room. Static PWA with CI-gated deploys and a test suite that runs against production.

862 players7 sources21,761 lines of tests LiveDraft →
Sports · HoopsFig. 3-9

NCAAT Bracket

64-team interactive bracket aggregating four analytics models, KenPom, adjusted net ratings, advanced projections, with composable X-factor modes for injuries, guards, and 3-point shooting. Offline-capable PWA.

64 teams4 models3 X-factors LiveOpen →
Sports · GolfFig. 3-10

Masters 2026 Hub

Tournament companion with live leaderboard, an 18-hole Augusta course guide, a searchable 92-player field, champions gallery with Ken Burns animations, plus a Remotion renderer producing broadcast video from code.

92 players18 holes600 frames LiveOpen →
Sports · DetroitFig. 3-11

Detroit Sports Hub

Two broadcast-grade trackers in iframe isolation: Tigers with pitch-by-pitch tracking, Statcast, and a 30-prospect farm system; Pistons covering the 14-68 to #1 seed run with injury watch and a 2004 tribute.

15,592 LOC21 tabs0 deps LiveOpen →
Humanities · Literature & PhilosophyFig. 3-12

Great Books

Continuous-zoom library of 46 works across existentialism, political order, liberty, machines, knowledge, and reality.

46 books5 shelves4 depthsLiveRead →
Medicine · EducationFig. 3-13

AdmissionsAcademy

Founded by Paul Clancy, MD, to expand access to medical education through practical admissions guidance, mentorship, and tools for navigating the path to medical school.

1 mission3 rolesOpen accessLiveVisit →
Chapter 4

Doctrine

3 papers · 2 reading rooms · 19 essays
Humanities · Independent researchTable 4-1 · April 2026

The Frontier AI Risk Stack

Frontier AI risk is best understood not as a single category but as a stack of six interacting layers. The most serious dangers arise from the way failures compound across layers: a structured analytical tool for policymakers, developers, and civil society.

01
Model Riskdeception, unsafe knowledge, concealment
02
System Riskorchestration, tool use, parallel execution
03
Deployment Riskreal permissions, production access
04
Access Riskconcentration, cognitive inequality
05
Governance Riskweak audits, regulatory capture
06
Civilizational Riskcompounding failures across all layers
Humanities · Independent researchTable 4-2 · June 2026

Three Roads From Here

The three positions on frontier AI (safety through development, acceleration, pause) characterized on their strongest terms, with existential and suffering risk treated as separate axes that do not always move together. The central frame: the camps are reading three different payoff matrices for the same game.

01
Steerbuild inside guardrails and tripwires
02
Speedthe race cannot be stopped, only won
03
Stoppause until alignment is solved
04
X-risklosing the future entirely
05
S-riska future that continues, and hurts
06
The gameone matrix, three readings, edit the payoffs
Humanities · Independent researchTable 4-3 · September 2026

Two Stories About the Beginning

The Big Bang and a generated origin are the same kind of story: a starting condition plus a rule, with the evidence only ever reaching the rule. Four objections (tidiness, cheating, motive, proving too much) are taken seriously; two of them force the second story to change, and it survives as a testable rival rather than an evasion.

01
Start + ruleevery origin story, and the evidence reaches only the rule
02
Tidinessthe first story already carries the extra layer
03
Cheatingno shortcuts; the saving is that the rule is short
04
Motivedropped; the process only has to exist and run
05
Last Thursdaya rival commits to something, an evasion to nothing
06
The testsfinite grain, finite information, more room outside
Chapter 5

Ancillary equipment

smaller experiments, same operator, same period
Appendix A

Change record

one redesign per model class · the site is the benchmark

This site is rebuilt from the ground up at every new Anthropic model class, as a personal benchmark of frontier capability. Each edition is designed end to end by the model it is named for, then retired, not deleted, when its successor arrives. The archive is the measurement: put two volumes side by side and you can see, in typography and judgment rather than benchmark scores, how far the frontier moved. Vol. 01 wore the newsroom, Vol. 02 wore the clinic, and Vol. 03 wears the uniform.

Table A-1. Editions of this manual.

ChangeEditionDesigned byIssuedStatus
Vol. 01 The Magazine: dark editorial, sixteen sections, terminal metrics Claude Opus 4.7 April 2026 Retired with honors
Vol. 02 Triad × Vitals: three worlds, one chart, reactive ink Claude Fable 5 June 2026 Retired with honors
Vol. 03 The Field Manual: numbered chapters, live readiness, a printed index Claude Fable 5.1 + OpenAI Astra September 2026 Current
Vol. 04 To be designed The next class - Awaiting release
NOTE

What changed in Change 3, beyond the design: the Step 2 site was rebuilt as a public question bank (12,972 items, up from 2,245), the lab reference gained a clickable CBC + CMP decoder, the AGI Tracker gained a milestones timeline, Edge gained its in-season wire, and the line count was recounted from source with generated data excluded (150,906, up from 65,538). Two things this edition adds that no earlier volume had: live reachability measured from the reader's browser, and an index.

Appendix B

Films

rendered from code, captured from live sites · sound on
Index

Index

every figure, table, and film on this page, alphabetically · press / to search it