A public, pre-registered experiment

The Honest Bot Experiment

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

LIVE: day 27 of 131Read the pre-registration

Scoreboard

Trendline

LONG

$102,701

+2.70%

vs Benchmark: 0.00 pp

Benchmark

LONG

The bar to clear

$102,701

+2.70%

Coinflip

CASH

$101,803

+1.80%

vs Benchmark: -0.90 pp

Snapback

CASH

$101,177

+1.18%

vs Benchmark: -1.52 pp

Oracle

CASH

$100,226

+0.23%

vs Benchmark: -2.47 pp

Equity curves

$96.9k$99.1k$101.2k$103.4kJul 6Jul 13Jul 20Jul 28Aug 4Aug 11
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+2.70%2.053.38%1
Snapback+1.18%4.030.23%4
Oracle+0.23%1.400.28%2
Benchmark+2.70%2.053.38%1
Coinflip+1.80%1.753.42%16

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: August 12, 2026

TrendlineLONG
close
770.56
sma200
703.993
SnapbackCASH
rsi2
39.4165
Oracleno signal
BenchmarkLONG

always LONG

Coinflipno signal
DateSignalsActivity
Aug 12TLSCO·BLC··
Aug 11TLSCOCBLCCCoinflip SELL @ 774.53
Aug 10TLSCOCBLCL·
Aug 7TLSCOCBLCLCoinflip BUY @ 771.02
Aug 6TLSCOCBLCC·
Aug 5TLSCOCBLCCCoinflip SELL @ 775.85
Aug 4TLSCOCBLCL·
Aug 3TLSCOCBLCLCoinflip BUY @ 749.44
Jul 31TLSCOCBLCCSnapback SELL @ 744.68
Jul 30TLSLOCBLCCSnapback BUY @ 736.05
Jul 29TLSCOCBLCC·
Jul 28TLSCOCBLCCCoinflip SELL @ 739.19
Jul 27TLSCOCBLCLCoinflip BUY @ 744.91
Jul 24TLSCOCBLCCCoinflip SELL @ 738.51
Jul 23TLSCOCBLCL·
Jul 22TLSCOCBLCLSnapback SELL @ 746.62Coinflip BUY @ 746.62
Jul 21TLSLOCBLCCSnapback BUY @ 746.29Coinflip SELL @ 746.29
Jul 20TLSCOCBLCLCoinflip BUY @ 747.06
Jul 17TLSCOCBLCCCoinflip SELL @ 742.08
Jul 16TLSCOCBLCLCoinflip BUY @ 752.76Oracle SELL @ 752.76

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.

56 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.