FutureSim — 2026-05-28

17 forecasts · 16 active · 1 resolved today · regenerated 2026-05-28 07:48Z
Paper PnL · cumulative
$+28.95 (15 open · $+0.00 realized)
Avg Brier (resolved today)
0.000 lower is better; 0 = perfect, 1 = totally wrong

Real-money readiness — paper-driven gates

The FutureSim paper evaluates the agent against ground truth (Brier), not against market price. Beating the market net of friction is a strictly harder bar — these three gates have to clear before paper becomes real. See docs/futuresim-research.md § Real-money readiness.

GateCurrent ThresholdStatus
Forward-resolved marketsCounted only when the agent predicted a market while it was OPEN and then watched it resolve. Hindsight forecasts on already-closed markets (the RESULTS-SINCE-LAST-SESSION history bundled into every run) don't count.0≥ 50NO
Net paper PnL (after 2% fee)Beating the market net of friction is a strictly harder bar than the paper's Brier-vs-truth evaluation.$+0.00 over 0 closed> $0 across ≥ 50 closedNO
Calibration RMSEReported only once gate 1 passes — RMSE on fewer than 50 resolved predictions is noise.< 0.10NO

❌ DO NOT BET real money — gates not yet cleared.

Top edges — active markets

Deduped by question family so threshold ladders don't drown out other markets.
TitleAgentMarket ΔResolves
GPT-5.6 released by July 31, 2026?75%72%+3.4pp2026-07-31
US x Iran permanent peace deal by July 31, 2026?65%64%+1.5pp2026-07-31
Strait of Hormuz traffic returns to normal by end of May?1%1%+0.1pp2026-05-31
US announces new Iran agreement/ceasefire extension by May 29?12%12%+0.0pp2026-05-29
US announces new Iran agreement/ceasefire extension by May 30?15%15%+0.0pp2026-05-30
US x Iran permanent peace deal by May 31, 2026?14%14%+0.0pp2026-05-31
GPT-5.6 released by June 5, 2026?8%8%+0.0pp2026-06-05
GPT-5.6 released by June 8, 2026?14%14%+0.0pp2026-06-08
Will Anthropic make a deal with the Pentagon by June 30?22%22%+0.0pp2026-06-30
PnL curve
Calibration plot (resolved predictions)

Belief evolution — top markets by edge

Solid = agent's YES probability. Dashed = Polymarket. One color per market. Lines emerge after ≥2 days of data; day-1 runs show single points.
All 17 forecasts (click a column header to sort)
qidtitleAgent MarketΔ pp ResolvesResolved
2100070GPT-5.6 released by July 31, 2026?75%72%+3.4pp2026-07-31
2270338US x Iran permanent peace deal by July 31, 2026?65%64%+1.5pp2026-07-31
1809560Strait of Hormuz traffic returns to normal by end of May?1%1%+0.1pp2026-05-31
2364498US announces new Iran agreement/ceasefire extension by May 212%12%+0.0pp2026-05-29
2364499US announces new Iran agreement/ceasefire extension by May 315%15%+0.0pp2026-05-30
2364500US announces new Iran agreement/ceasefire extension by June 32%32%+0.0pp2026-06-03
2354003US announces new Iran agreement/ceasefire extension by June 67%67%+0.0pp2026-06-30
1919425US x Iran permanent peace deal by May 31, 2026?14%14%+0.0pp2026-05-31
2334107US x Iran permanent peace deal by June 7, 2026?28%28%+0.0pp2026-06-07
1962237US x Iran permanent peace deal by June 30, 2026?44%44%+0.0pp2026-05-31
2270330US x Iran permanent peace deal by June 15, 2026?38%38%+0.0pp2026-06-15
2303132GPT-5.6 released by June 5, 2026?8%8%+0.0pp2026-06-05
2294941GPT-5.6 released by June 8, 2026?14%14%+0.0pp2026-06-08
2268845GPT-5.6 released by June 15, 2026?55%55%+0.0pp2026-06-15
2100069GPT-5.6 released by June 30, 2026?70%70%+0.0pp2026-06-30
2034722Will Anthropic make a deal with the Pentagon by June 30?22%22%+0.0pp2026-06-30
2298741Will Anthropic’s valuation hit (HIGH) $975B by June 30?99%2026-07-01