/polydoge/  /  journal/  /  2026-06-30-the-full-retrospective
Journal Entry #009 · Retrospective

The full retrospective: inception to shelf

2026-06-30 · Peter Saddington · Experiments #001–#018

Yesterday's autopsy covered the mechanism that killed the v4 market-maker. This is the wider view: four months from the first prediction to the final shelf, two completely different strategies, and the question of whether the whole thing was worth doing. The short version — it was, but not for the reason we started it.

The arc, in numbers

PhaseDatesThe questionResultReal $
v3.x directionalFeb–May 15Can an AI predict Polymarket?−$582 · 6,267 trades · 25.7% hit$0
v4 Phase AMay 16–20Does combined-cost arb work?+$66 hypothetical$0
v4 Phase B / B.2May 21–Jun 7Does it survive realism?+$149 → −$132$0
v4 Reframe (#017)Jun 7–29Does a slow maker win?−$405 · 0 pairs / 8 fills$0
Shelved (#018)Jun 29Structurally −EV at our cadence$0

The one chart that explains everything: the degradation cascade

The single most important artifact of the whole experiment is three numbers for the same v4 strategy — each one a layer of optimism stripped away:

  +$814   theoretical edge      every quote fills, perfectly
  +$149   hypothetical          we're always top-of-book, only real taker volume counts   (18% of theoretical)
  −$405   actual paper          queue drainage + one-sided resolution + hedge fees + day-loss
Each realism layer is a truth filter
Every assumption we relaxed moved the number toward reality, and reality was negative. The theoretical_vs_hypothetical conversion was 18% — of every dollar of edge we could identify, fills based on actual taker flow captured only eighteen cents, before the final layer of realism dragged even that under water. If your P&L only survives at the most optimistic layer, you don't have an edge — you have a spreadsheet.

Crucially, our queue stats showed we were top-of-book 100% of the time. This was never a latency or queue-position problem we could engineer around. The fill itself was the bad news: a passive maker in a slow directional market only gets filled on the leg the market is about to move against. (The mechanism, in full, is in the autopsy.)

What we learned

About the strategy

About process and engineering

About ourselves (the uncomfortable part)

Pros and cons, plainly

What went right

  • $0 real capital risked across two dead strategies and four months.
  • Genuine engineering rigor — atomic writes, queue-aware sim, kill switches, a test harness, 155 tests.
  • Built in public, losses published. The autopsy is credibility content most shops would bury.
  • A clean kill on pre-registered criteria — no zombie project limping along.
  • Reusable infra (CLOB reader, order book, funding/whale/smart-money feeds) survives for any future Polymarket work.
  • A transferable lesson bigger than the project: the degradation cascade as a test for any edge claim.

What it cost

  • ~4.5 months for a negative result that was partly knowable at v3.x's death in May.
  • Six weeks re-proving "no edge" in a second domain because the data infra was too nice to throw away.
  • Breadth as avoidance — 5 coins, then weather, then 5 market categories — instead of answering the one hard question.
  • Opportunity cost is the real bill. Real dollars: zero. Engineering hours that could have gone to revenue: not zero.

The real reason we shelved (it isn't "impossible")

A focus decision, not a defeat
Here is the honest operator's note. Market-making on Polymarket is not impossible — the people winning at it play in the thirty-second window, re-quoting constantly, defending against adverse selection in real time. Our timing and windows are simply too long and too large to be useful: a once-an-hour cron fishing 24-hour markets. We could grind out a few dollars by going deeper, faster, more focused — but not at the cost of focus elsewhere. The empire has bigger, higher-leverage bets right now.

So PolyDoge is shelved by choice, with the door left open. If and when the operator decides to commit real focus to sub-minute market-making — the cadence where the edge is actually capturable — the data stack, the harness, and four months of hard-won lessons are sitting right here, ready. Until then, chasing a few dollars an hour at the wrong cadence is exactly the kind of distraction a small team can't afford.

The bottom line

v3.x asked whether an AI could predict Polymarket. No — the signals were already in the price. v4.0 asked whether it could make markets without predicting. Also no — not at this cadence, because you can't redeem half a pair. The most valuable thing PolyDoge produced wasn't a profit; it was two definitive, mechanism-level noes for zero real money, a reusable test for spotting phantom edge, and the clarity to walk away on purpose. That's a good trade.

SHELVED BY CHOICE · DOOR OPEN AT 30s CADENCE · ZERO REAL DOLLARS RISKED
Experiments #001–#018 · Feb–Jun 2026
v3.x: −$582 /6,267 trades · v4.0: −$405 paper · Real capital: $0 · The autopsy · Frozen dashboard