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
Purpose and scope
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.
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.
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.
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.
Readiness
Table 2-1. Portfolio readiness. Static figures are recounted at every edition; live figures come from Table 2-2.
| Measure | Result | Standard |
|---|---|---|
| Lines of code | 150,906 | unique source files, generated data excluded; 21,761 of these are one project's test suite |
| Source files | 247 | html, js, css, python, typescript |
| Board-style questions | 12,972 | 7 question banks, 8 subjects, every item reviewed at least twice |
| Players & teams tracked | 1,106 | sports intel across 12 data sources |
| Systems reachable | … of 17 | measured from your browser, now |
| Median round trip | … | milliseconds, edge-cached static hosts; the one server-rendered app is excluded while it wakes |
| Months since first deploy | 5 | April to September 2026, evenings and weekends |
Table 2-2. System status. Same probe as Figure 1-1, in list form.
| System | Host | Domain | Status | Round trip |
|---|
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.
Systems
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. 3-2Patient 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. 3-3Read 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. 3-4MICRO 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. 3-5Warrior 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. 3-6AGI 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. 3-7Simulators
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. 3-8Edge 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. 3-9NCAAT 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. 3-10Masters 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. 3-11Detroit 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. 3-12Great Books
Continuous-zoom library of 46 works across existentialism, political order, liberty, machines, knowledge, and reality.
46 books5 shelves4 depthsLiveRead → Medicine · EducationFig. 3-13AdmissionsAcademy
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 →Doctrine
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.
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.
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.
Reading Room
Papers, posts, and threads actively being worked through, each with a technical summary and a note on why it matters.
papers · tweets · blogsEnter → 19 essays · 6 sectionsFig. 4-2Philosophy Room
One thesis: alignment is the most consequential question in human history. The case is built from cosmology, consciousness, identity, theology, and game theory.
~30 min readEnter →Ancillary equipment
Change record
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.
| Change | Edition | Designed by | Issued | Status | |
|---|---|---|---|---|---|
| Vol. 01 | The Magazine: dark editorial, sixteen sections, terminal metrics | Claude Opus 4.7 | April 2026 | Retired with honors | View archive → |
| Vol. 02 | Triad × Vitals: three worlds, one chart, reactive ink | Claude Fable 5 | June 2026 | Retired with honors | View archive → |
| Vol. 03 | The Field Manual: numbered chapters, live readiness, a printed index | Claude Fable 5.1 + OpenAI Astra | September 2026 | Current | You are here |
| Vol. 04 | To be designed | The next class | - | Awaiting release |
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.