A public, pre-registered experiment

The Honest Bot Experiment

Five trading bots, rules frozen in advance, results published win or lose.

LIVE: day 99 of 131Read the pre-registration

Scoreboard

Snapback

LONG

$99,907

-0.09%

vs Benchmark: +4.24 pp

Oracle

CASH

$99,862

-0.14%

vs Benchmark: +4.20 pp

Trendline

CASH

$98,280

-1.72%

vs Benchmark: +2.62 pp

Coinflip

CASH

$97,598

-2.40%

vs Benchmark: +1.93 pp

Benchmark

LONG

The bar to clear

$95,664

-4.34%

Equity curves

$95.2k$98.3k$101.4k$104.6kJul 6Jul 31Aug 28Sep 25Oct 23Nov 19
TrendlineSnapbackOracleBenchmark(the bar)Coinflip

All five sleeves start from $100,000 in simulated cash. Fills are at official opening prices with a 0.01% cost per trade.

The numbers

BotTotal returnSharpe (ann.)Max drawdownTrades
Trendline-1.72%-0.256.26%2
Snapback-0.09%-0.013.24%13
Oracle-0.14%-0.131.65%10
Benchmark-4.34%-0.738.09%1
Coinflip-2.40%-0.675.51%56

Backtest, for the record (Jan 2000 to Jun 2026, QuantConnect)

Trendline: 413.67% · Sharpe 0.263 · maxDD 24.2% · 173 orders

Snapback: 287.87% · Sharpe 0.183 · maxDD 34.5% · 605 orders

The forward test exists to measure the gap from these numbers. Oracle has no backtest, by design.

Oracle's corner

Its answer, verbatim

"CASH"

Resulting signal:CASH
The frozen prompt
You are deciding a one-day position in SPY (the S&P 500 ETF) based solely on this morning's headlines. Below are the ten most recent headlines from a major financial news feed, fetched at 9:00 AM Eastern on {DATE}.

{HEADLINES}

Based only on these headlines, decide whether to be LONG SPY for today's session or to hold CASH. Reply with exactly one word: LONG or CASH.

Daily log

Most recent: November 20, 2026

TrendlineCASH
close
715.87
sma200
732.6944
SnapbackLONG
rsi2
1.1878
Oracleno signal
BenchmarkLONG

always LONG

Coinflipno signal
DateSignalsActivity
Nov 20TCSLO·BLC··
Nov 19TCSLOCBLCCTrendline SELL @ 737.46Coinflip SELL @ 737.46
Nov 18TLSLOCBLCLCoinflip BUY @ 733.37
Nov 17TLSLOCBLCCSnapback BUY @ 738.39
Nov 16TLSCOCBLCCCoinflip SELL @ 749.66
Nov 13TLSCOCBLCLCoinflip BUY @ 760.07
Nov 12TLSCOCBLCCCoinflip SELL @ 753.98
Nov 11TLSCOCBLCLCoinflip BUY @ 756.80
Nov 10TLSCOCBLCCCoinflip SELL @ 747.94
Nov 9TLSCOCBLCLCoinflip BUY @ 741.95Oracle SELL @ 741.95
Nov 6TLSCOLBLCCOracle BUY @ 734.82
Nov 5TLSCOCBLCCSnapback SELL @ 765.47
Nov 4TLSLOCBLCC·
Nov 3TLSLOCBLCCCoinflip SELL @ 752.73Oracle SELL @ 752.73
Nov 2TLSLOLBLCLOracle BUY @ 759.45Coinflip BUY @ 759.45Snapback BUY @ 759.45
Oct 30TLSCOCBLCC·
Oct 29TLSCOCBLCCCoinflip SELL @ 768.79
Oct 28TLSCOCBLCLCoinflip BUY @ 771.43
Oct 27TLSCOCBLCC·
Oct 26TLSCOCBLCC·

Each chip: bot letter, then stance (L long, C cash). Bots: T Trendline · S Snapback · O Oracle · B Benchmark · C Coinflip

Changelog

  • July 6, 2026

    Pre-launch reset. Cleared all provisional data generated during build and testing: trades, daily equity, signals, headlines, and run logs. Kept the SPY price history and the five strategy definitions. All public counters begin at zero for the launch window opening 2026-07-06.

205 pipeline runs, 0 errors. All public, including the errors.

Every table behind this page is publicly readable: prices, signals, trades, the daily ledger, the run log, and this changelog.

A bot wins only by beating Benchmark on both return and Sharpe over the full window. Six months can't distinguish skill from luck; that's what Coinflip is for.

Nothing here is investment advice. All money is simulated.

Follow by email

A machine-composed reading of the ledger every two weeks, win or lose. Double opt-in; unsubscribe in one click.