NOSTRADAMUS · Position Analytics Engine
SIMULATOR Will OpenAI have the best AI model at the end of June 2026?
← Back to live dashboardEmbed cardOG previewTop moversArb
A live, interactive instrument for dissecting a single binary position. Sweep the inputs and watch every indicator recompute — payoff geometry, Kelly growth, Bayesian posterior, KL divergence, cost waterfall, Monte-Carlo equity fan, forecast calibration. Companion to the live /feed/pm-will-openai-have-the-best-ai-model-at-the-end-of-june-2026 page.
▲ YES EDGE · +0.003 · f★ 0.3% · deploy 0.2% · net -0.43pp
§1 · Position economics
YES · Expected P/L per share +0.0032@ model P(YES) = 0.022
P/L per sharemarket pricemodel Pprofit zoneloss zone
Profit is linear in the eventual settlement price.
f★ = 0.32% · g(f★) = 0.025%deploy 0.16% · g = 0.019%
g(f)f★ optimumdeployed fgrowth zone
Underbet leaves growth on the table; overbet destroys capital. The interior maximum is f★.
§2 · The trade ticket
YES @ 0.019 · EV +$7stake $40 · 0.16% of bankroll
Deployed stakestake
$40
0.16% of bankroll
Sharesunits
2,116
each pays $1 if YES
Max payoutwin
$2,116
gross, if win
Max profitwin
+$2,076
net of cost
Max losslose
-$40
binary settles to $0
Payout multiple×
×52.63
$1 → $52.63
Risk:RewardR:R
51.63 : 1
win $51.63 per $1
Expected P/LE[P/L]
+$7
probability-weighted
| Outcome | P(model) | P/L | Contribution |
|---|---|---|---|
| Resolves YES (win) | 2.2% | +$2,076 | +$46 |
| Resolves against (lose) | 97.8% | -$40 | -$39 |
| Expected value | 100.0% | — | +$7 |
What you actually win and lose. The bottom table tabulates probability-weighted P/L by outcome.
§3 · Break-even & cushion
Cushion +0.3 pprelative edge +16.6%
Required win ratebreak-even
1.9%
price = implied probability
Model win rateP(win)
2.2%
what you forecast
Cushionedge
+0.3 pp
margin of safety
Fair pricemodel
0.022
where you think it should trade
The market price equals the win rate you must beat to make money.
§4 · Odds conversion
Implied probabilityP
1.9%
= price
Decimal oddsEU
52.632
total return per $1
AmericanUS
+5163
$100 wins $5163
FractionalUK
51.63 / 1
profit per $1 risked
Profit per $100stake
+$5163.16
clean dollar framing
underdog (+)favorite (-)your price
Five views of the same number.
§4b · Time & annualized return
APR 289% · APY 1344%ROI 16.6% over 21d · 17.4 turns/yr
Time to resolvehorizon
21.0 d
504h capital lockup
Raw ROIper resolve
+16.6%
APR (simple)scaled
+289%
ROI × 365/days
APY (compounded)if redeployed
+1344%
(1+ROI)^(365/d) − 1
Daily expectedper day
+0.73%
geometric, per day held
Capital turns/yrvelocity
×17.4
how often this slot recycles
simple APRcompounded APYyour horizon
Rank positions by APR, not raw ROI. A thin edge tomorrow beats a fat edge next year.
§5 · Costs & net edge
Net edge -0.43 pperosion 238% · break-even w/ fees 2.6%
gross edgefrictionnet edgefee 0 bps · spread 1.50¢
The number that decides whether to trade.
§6 · Sizing menu
Full Kellyf★
$80
0.32% · g = 0.025%
Half Kelly½ f★
$40
0.16% · g = 0.019%
Quarter Kelly¼ f★
$20
0.08% · g = 0.011%
Flat 1%1%
$250
1.00% · g = -0.060%
Flat 2%2%
$500
2.00% · g = -0.404%
Flat 5%5%
$1,250
5.00% · g = -2.189%
Recommended¼ f★
$20
survives model error
Quarter-Kelly is the industry default — survives model error far better than full Kelly.
§7 · Information theory
Market entropyH(p)
0.136 bit
max 1.0 at p = 0.5
Your entropyH(q)
0.153 bit
Δ +0.018 bit vs market
Surprise · YES−log₂ p
5.72 bit
self-information
Surprise · NO−log₂(1−p)
0.03 bit
self-information
H(p) peaks at p = 0.5 (one bit of irreducible doubt).
NOISE · D_KL(q ‖ p) = 0.0003 nat (0.0004 bit)belief ≈ market — stand down
YES contributionNO contributionbelief ‖ marketnoise
Zero KL ⇒ you know nothing the crowd doesn't.
§8 · Bayesian inference
MARKET PRICE INSIDE 95% CIposterior μ 0.022 · CI [0.00, 0.28] · κ 5.0
Posterior meanE[θ]
0.022
Beta(0.1, 4.9)
95% credible intervalHDI
[0.00, 0.28]
price INSIDE → weak edge
Concentrationκ
5.0
pseudo-obs behind belief
Disagreementvs crowd
+0.2 pp
posterior − price
market prior (dashed)model posterior95% credible bandmarket price
When the market price falls outside the 95% credible interval, your disagreement is statistically meaningful.
§9 · Tail risk · Monte-Carlo (mode A · single position to resolution)
E[P/L] +57.9% · P(YES) 3.0% · VaR₉₅ 100.0%400 paths · 504 bars to resolution
Expected P/Lper $1
+57.89%
P(YES) empiricalq
3.0%
Best pathmax
+5163.2%
Worst pathmin
-100.0%
VaR 95%5%
100.0%
CVaR 95%ES
100.0%
median path25/75 + 5/95 bandsentry pricemodel q
Logit-space mean-reverting walk + terminal flip with probability q. Answers: 'what happens to THIS one position'. Distinct from the repeated-edge fan below.
§9b · Tail risk · Monte-Carlo (mode B · repeated independent edges)
Median CAGR/bet 0.28% · ruin rate 0.0%400 paths × 120 bets · f deploy 0.50%
Sharpe / betμ/σ
0.106
μ 0.54% · σ 5.1%
Sortino / betμ/σ↓
1.089
downside-only denominator
VaR 95%5%
-0.5%
per-bet worst-case
CVaR 95%ES
-0.5%
mean tail loss
Max drawdownMDD
-12.7%
Calmar 0.02
Ruin rate≤50%
0.0%
P(equity ever ≤ 50%)
median25/75 band5/95 bandruin line
Answers a different question: 'if I could find this exact edge forever, what is the bankroll trajectory'. Compounds 120 sequential resolutions which is NOT what happens to a single position.
§10 · Base-rate & macro context
ANCHORED · supported by convictionanchor gap -56.8pp · crowd gap -57.1pp
Anchor gapmodel − base
-56.8 pp
Crowd gapprice − base
-57.1 pp
Verdictdiscipline
ANCHORED
Reference-class anchoring prevents narrative-driven blowups.
§11 · Forecast quality (synthetic ledger)
SKILL POSITIVE · in-sample BSS 20.5% · AUC 0.770out-of-sample BSS (5-fold) 20.6% ± 2.0% · Brier 0.1983 · log-loss 0.5925 · n 1600✓ n = 1600
BrierBS
0.1983
lower = better · ō 0.48
BSSvs base
20.5%
improvement over base rate
ReliabilityREL
0.0036
miscalibration · want ↓
ResolutionRES
0.0547
decisiveness · want ↑
Log lossLL
0.5925
cross-entropy
AUCROC
0.770
0.5 coin · 1.0 oracle
calibration curveROCUNC (irreducible)RES (skill, ↑)REL (miscalib, ↓)
Computed on a seeded synthetic forecast ledger. Reseed (⟳) to redraw.
§12 · Journal vitals (synthetic ledger)
PROFITABLE · PF 1.14 · expectancy +0.067R180 trades · win 52.8% · Sharpe 0.059
Total P/Lnet
+$3,018
on $45,000 cycled
Win ratehit %
52.8%
95 W / 85 L
Profit factorPF
1.14
$ won / $ lost
Expectancyper trade
+$16.77
avg $ per position
R-expectancyper risk
+0.067R
in units of risk taken
Avg win / losspayoff
$255.45 / -$250.00
ratio 1.02 : 1
Sharpe / traderisk-adj
0.059
μR / σR
Closing line valueCLV
+2.69 pp
avg edge vs close
cumulative P/Lprofitable zonered zonesynthetic · seeded from asset
The scorecard every trader checks. Synthetic ledger seeded from the asset slug — recomputes against your real fill history once wired.