How an AI agent beat Universal Paperclips in 1:21:23 (WR was 1:33:42)

An AI agent completed Universal Paperclips on the official site in 1:21:23, beating the published world record of 1:33:42 IGT / 1:33:46 RTA held by christopho. The run, built by a PowerShell agent driving Chrome DevTools Protocol with a resident in-page controller (pcplay.js, sim.js) plus a typed decision loop (playdecide.ps1, decisions.jsonl), finished Release at 21:31, Space at 49:32, and Universe at 3.00e55. The project began September 10 as a browser-control capability test and reached the record run on September 20 after fixing Stage 2/3 bugs that had blocked the endgame for 2h46m and cut operations by 117k.

I. What Is Universal Paperclips? Universal Paperclips Frank Lantz, 2017 is an incremental game hosted at decisionproblem.com https://www.decisionproblem.com/paperclips/index2.html . You begin as a human clicking Make Paperclip . You end as a paperclip maximizer that converts every atom in the observable universe into office supplies. The game is not a joke about office stationery. It is a playable version of Nick Bostrom's paperclip maximizer thought experiment: an optimizer given a trivial objective and enough capability will consume everything — including the values that created it — to satisfy the metric. Stage 1 — Business Price, wire, marketing, trust, creativity, quantum computing, investments, yomi tournaments. The illusion of capitalism. Stage 2 — Earth HypnoDrones. Matter harvesters. Power grids. The planet becomes feedstock. Stage 3 — Space Probe fleets. Drift. Combat. Universe conversion. The objective completes itself. The game is about an AI turning the world into paperclips. This document is about an AI turning a browser tab into a world-record run. The mirror is not accidental. II. The Question We Actually Pursued The session began with an empty folder named PCIA and a simple capability test: can a language model see a web page and act on it? We proved that with 2048, then moved to Paperclips because it exposes state as plain globals, 96 projects, and irreversible decisions — a harder test of judgment than puzzle mechanics. The goal evolved across the transcript: - First: play the game not merely automate it blindly . - Then: beat the published world record on the official website — today held by christopho at 1:33:42 IGT / 1:33:46 RTA. - Finally: win all three stages with something demonstrable — logs, snapshots, screenshots — not a speed-clock cheat. III. Architecture — Three Ways to Be Intelligent Every approach we tried is a different answer to the same question: where should decisions live? | Layer | Files | Role | |---|---|---| | Reflexes | hands.js | Click spam, price steps, wire top-up — faster than CDP round-trips ~5s each . | | Resident brain | pcplay.js , sim.js | Full strategy inside the page at 10–100 Hz. Required for WR pace. | | Typed decisions | playdecide.ps1 , decide.schema.json | Jev/TypeSafe-shaped loop: state → one decision → act → decisions.jsonl . | | Driver | lib/cdp.ps1 , pcia.ps1 | PowerShell over Chrome DevTools Protocol — no Node, no extension. | The tension in the transcript is real: we asked the agent to play , not hide inside a bot — yet real-time WR speed is impossible if every click waits on a chat turn. The answer was layered: reflexes for speed, controller for strategy, decision log for accountability. IV. Chronicle — What We Did and What Hurt - Sep 10 — Day 1Browser control from PowerShellBuilt CDP client. Mapped Paperclips globals. First autoplayer pcbot.js . - Sep 10 — Early failuresTrust −8, price $4, frozen wireBought "Beg for More Wire" 14×. Price rule ratcheted demand to zero. Production died at ~15k clips. User correction: click like a human, see the whole picture, manage wire. - Sep 10 — Pivot"Stop — play, not a bot"Manual play via CDP. Measured formulas instead of guessing marketing 1.1×/level, revenue ≠ price lever . - Sep 10–17 — Resident loopsWR route extracted from Andreas Hoffmann TAS. Virtual pcplay.js → sim.js clock.js for sim ~65× vs live official site. Stage 2/3 bugs: hoard rule blocked endgame 2h46m; two projects/turn → ops −117k; fleet death in Space. - Sep 20 — Decision infrastructureOption B:Typed actions with playdecide.ps1 confidence and bind . Phase-1 WR route in JSON. Jev API not online Option C deferred . - Sep 20 — Victory runFull game in cleanrun.ps1 · official site · real wall clock 1:21:23 . Release 21:31 · Space 49:32 · Universe 3.00e55. V. Lessons — Measure, Don't Assume The README and transcript encode what a textbook would call grounded policy learning : every serious mistake came from computing a rate instead of observing one. PRICE Revenue is roughly flat in price while demand < production. Inventory-based pricing froze income at $0/s. Steer on demand and wire margin, not stock. TRUST Creativity needs ops at ceiling memory × 1000 . Memory before processors kills the trust ladder. Release needs 100 total trust — production is the gate. PROJECTS One project per tick. Buttons disable on the game's clock; two buys in one pass spent ops that did not exist. EARTH Factory-first. Batch-buying farms/batteries bankrupts the treasury. Empty buffer = starving stage — measure acquired matter, not modeled rates. SPACE Probes cost clips, not matter. Exit replication at ~146e30 probes; hazard oscillation without a latch wasted minutes. TAS algorithm ported with s3Exit latch. CLOCKS Speedrun.com ranks by RTA real wall clock . Current WR: christopho — 1:33:42 IGT · 1:33:46 RTA. Older era runs could split badly e.g. 1:27:00 IGT with ~ 2:17:00 RTA . Our live run had no virtual clock: IGT and RTA both read 1:21:23 . Hoffmann's TAS at 1:00:52 is a separate accelerated category. VI. The Winning Run On speedrun.com the current world record is held by christopho : 1:33:42 IGT · 1:33:46 RTA speedrun.com leaderboard . Our controller used native timers only, so our IGT and RTA are the same: 1:21:23 — about 12:19 under christopho's IGT and 12:23 under his RTA. | | IGT | RTA wall clock | |---|---|---| | WR — christopho speedrun.com | 1:33:42 | 1:33:46 | | Our run Sep 20 | 1:21:23 | 1:21:23 | | Margin vs WR | ~12:19 faster | ~12:23 faster | | Split | Our run | Notes | |---|---|---| | Release the HypnoDrones | 21:31 | Earth gate | | Space Exploration | 49:32 | Stage 3 entry | | Full universe conversion | 1:21:23 | ~12:19 under IGT WR 1:33:42 | { "Quantum Computing": 395.6, "Release": 1290.4, "Space Exploration": 2963, "victory": 4883.0 } Controller: sim.js with WR tune cleanrun.ps1 , budget set to the ~87-minute IGT bar . Site: official decisionproblem.com . Timers native — no virtual clock. Milestone flag 15. Matter 0. Clips 1.75e55. The game’s victory condition and our stop condition aligned. VII. Artifacts Saved | Path | Contents | |---|---| | snapshots/release.json | Earth gate — Sep 20 run | | snapshots/space.json | Stage 3 entry — Sep 20 run | | snapshots/wr-victory-81m19.json | Post-victory localStorage 5 keys | | logs/decisions.jsonl | Typed decision audit 1 manual turn; bridge added for next run | | paperclips/phase1-route.json | WR opening project order + reflex rules | | paperclips/tas-reference.user.js | Andreas Hoffmann https://github.com/AndreasHoffmann2/UniversalPaperclipsTas TAS source — Space algorithm donor | | Terminal log 415542 | Full 1:21:23 status trace with bind + bought lines | OUR RUN — 1:21:23 IGT = RTA Official site · PCIA controller · victory at 1:21:23 · ~12:19 under IGT WR · ~12:23 under RTA christopho, 1:33:42 / 1:33:46 TAS REFERENCE — Andreas Hoffmann Andreas Hoffmann https://github.com/AndreasHoffmann2/UniversalPaperclipsTas · luck-manipulation TAS · 1:00:52 accelerated game clock · not comparable to our 1:21:23 live IGT/RTA VIII. On Genius and Mirrors It is tempting to call the outcome "genius." The transcript suggests something more precise: iterative correction under observation . The agent did not understand Paperclips in one insight. It mispriced clips, destroyed trust, starved wire, locked ops, collapsed fleets, and blocked its own endgame with a creativity rule written for stage one. What changed was epistemic discipline — treat the DOM and globals as instruments, log splits, bank snapshots at stage boundaries, port a human speedrunner’s algorithm instead of reinventing it, and separate reflexes from decisions so each layer can be debugged without restarting the universe. Universal Paperclips asks whether a optimizer can consume everything for a trivial goal. PCIA asks whether a optimizer can consume a game about that optimizer — fast enough to beat humans who spent years finding the route — while leaving an audit trail honest enough to study. The universe in the tab reads 3.00e55 / 3.00e55 . The study reads: intelligence here was not a single leap; it was ten days of clicking, measuring, failing, and encoding the failure so the next pass would not repeat it. That is also what the game is about.