A public, pre-registered experiment

The Honest Bot Experiment

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

LIVE: day 84 of 131Read the pre-registration

Scoreboard

Snapback

CASH

$102,271

+2.27%

vs Benchmark: +1.30 pp

Trendline

LONG

$100,975

+0.97%

vs Benchmark: 0.00 pp

Benchmark

LONG

The bar to clear

$100,975

+0.97%

Oracle

CASH

$99,825

-0.17%

vs Benchmark: -1.15 pp

Coinflip

CASH

$98,955

-1.04%

vs Benchmark: -2.02 pp

Equity curves

$96.8k$99.4k$101.9k$104.5kJul 6Jul 29Aug 20Sep 15Oct 7Oct 30
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+0.97%0.323.38%1
Snapback+2.27%1.831.32%10
Oracle-0.17%-0.420.68%6
Benchmark+0.97%0.323.38%1
Coinflip-1.04%-0.333.64%46

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 2, 2026

TrendlineLONG
close
755.72
sma200
728.8541
SnapbackLONG
rsi2
9.3379
Oracleno signal
BenchmarkLONG

always LONG

Coinflipno signal
DateSignalsActivity
Nov 2TLSLO·BLC··
Oct 30TLSCOCBLCC·
Oct 29TLSCOCBLCCCoinflip SELL @ 768.79
Oct 28TLSCOCBLCLCoinflip BUY @ 771.43
Oct 27TLSCOCBLCC·
Oct 26TLSCOCBLCC·
Oct 23TLSCOCBLCCCoinflip SELL @ 759.90
Oct 22TLSCOCBLCLCoinflip BUY @ 766.37
Oct 21TLSCOCBLCCCoinflip SELL @ 771.17Snapback SELL @ 771.17
Oct 20TLSLOCBLCL·
Oct 19TLSLOCBLCL·
Oct 16TLSLOCBLCLCoinflip BUY @ 773.24
Oct 15TLSLOCBLCCSnapback BUY @ 766.25Coinflip SELL @ 766.25
Oct 14TLSCOCBLCLCoinflip BUY @ 774.92
Oct 13TLSCOCBLCCCoinflip SELL @ 777.34
Oct 12TLSCOCBLCLCoinflip BUY @ 778.78
Oct 9TLSCOCBLCCCoinflip SELL @ 776.24
Oct 8TLSCOCBLCL·
Oct 7TLSCOCBLCLCoinflip BUY @ 775.77
Oct 6TLSCOCBLCCCoinflip SELL @ 778.15

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.

175 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.