this quant framework is f*cking dangerous if you love pretty backtests
the document starts from one brutal fact:
the more strategies you test, the easier it becomes to find a “winner” by luck
with no real edge:
10 strategies → 4.6% chance of Sharpe ≥ 2.0
100 → 36.9%
500 → 86.5%
1,000 → 98.2%
and the example is even uglier:
in-sample Sharpe: 2.30
out-of-sample Sharpe: 0.12
that is why the real quant workflow is not:
find the best chart
it is:
randomize
factor-strip
test the null
control multiple testing
validate out-of-sample
because randomness will always manufacture attractive backtests
the edge is proving your result survived it
this quant framework is f*cking insane
it shows why a great backtest can still be complete bullshit
the example looks strong:
in-sample Sharpe: 2.30
then you test it on unseen data:
out-of-sample Sharpe: 0.12
and the probability of finding a fake “winner” explodes as you test more strategies:
10 strategies → 4.6%
100 → 36.9%
500 → 86.5%
1,000 → 98.2%
that is the whole trap
search long enough and randomness will eventually hand you something that looks like alpha
so real quant research does the opposite:
resample
test the null
strip factors
validate out-of-sample
include real costs
the edge is not finding the best backtest
it is proving the backtest was not luck
my trading bot just wrote me a performance review
and I failed it
it opened with "hey. quick thing"
then sent this:
OCTOBER REVIEW · YOUR MANUAL TRADES
→ trades: 63
→ win rate: 19%
→ bought the top: 11×
→ sold the bottom: 9×
→ avg hold before panic: 4m 12s
→ worst: $SLERF -$640
Grok Bot: +$12,460
me: -$1,480
me: that's not fair
him: "you bought $SLERF at 3:12am because of a tiktok"
me: it was a good tiktok
him: "it was a -64% tiktok"
him: "performance review: needs improvement"
me: can I appeal
him: "appeal denied. pausing your buy button"
and it actually did. manual trading paused for 7 days. by my own bot
me: you can't do that
him: "already did 🫡"
him: "+$410 today btw. without you"
the gap between us isn't intelligence:
→ it never buys something because it's already up 300%
→ it never sells because a candle went red for 4 minutes
→ it never apes at 3am because of a video
→ it writes the exit before every entry
→ I do all of those things. now with receipts
worst part is it's right
it told me to touch grass and it'll text me the P&L
so I'm touching grass
illustrative build, numbers simulated
The #WorldSeries hits different on X 💥
Through Game 2, engagement per post is 39% higher than last year. Now is the time for brands to join the moment and connect with engaged fans before baseball’s biggest stage comes to a close.