A systematic trading lab, run in public: every result published, every number checkable

Most trading bots are slop. We have the receipts.

Every “build a bot, get rich overnight” video sells the same dream. We crunched 252,237 lines of code and research and ran 2,345 automated tests to find what's actually real, and killed 33 strategies that weren't. This isn't “don't build a bot.” It's how to not build a bad one, and go in knowing more than you would have. No hype, no signals, nothing to buy.

0
lines of code
0
automated tests
0
strategies killed
0
survived to a buyable bot
The data behind the kills
7.8M
order-book ticks in one investigation, over 41 days
15,992
liquidation cascades, one dataset attacked three ways
5,814
after-hours price-gap events, across 12 instruments
~90
chart-pattern hypotheses screened to surface these kills

Single investigations, not the total. The biggest sample we publish is 7.8 million ticks; the smallest kill is n=8, and we killed that one because eight trades is too few to trust.

Try it yourself

Watch a “winning” bot drain your money.

Our real HYPE-long bot won plenty of its individual trades and still lost 31.9% in a week, while holding the coin lost 11.5%. Put your number in; the return is locked to what it actually did.

Every kill on the ledger has this calculator
What it would have done to your money
You put in$10,000
You run it for1 week
You would have
$6,810
$3,190
lost (32%)
You started with$10,000
This strategy left you$6,810
Instead of buy and hold HYPE$8,850

Locked to this strategy's real measured result of -31.9% per week, compounded. You choose the amount and the time. We don't choose the return, the strategy already did.

Look inside the machine

Live data in. Dead strategies out.

A live slice of the market feed, and the research gauntlet it runs through: features become hypotheses, every hypothesis gets a pass/fail line locked in writing, and then the tests run. Almost nothing survives.

Hyperliquid · live funding rates
connecting…
The kill engine
179 test files
A pipeline diagram: market data flows through features, hypotheses, and pre-registered tests to verdicts, backed by 2,345 automated tests. Failed ideas fall into a graveyard tray. 33 strategies were published and killed; 0 survived to a bot you can buy.

The feed is live from Hyperliquid's public API. The flow is an illustration of the pipeline, not a measured throughput; the counts are real and re-derived from the repository.

See the full engine
The honest answer

So does anything actually work?

Yes, but rarely, and never the way the videos say. It comes down to four things, and none of them is a bot you can buy.

  1. 01
    Scale

    They have a lot of capital, and bet big.

    Size lowers the trading costs that quietly kill small accounts, and unlocks edges you can't run with $500. Not a clever bot, a different cost structure.

  2. 02
    Skill

    They trade better than today's retail AI.

    A tiny minority really read context and risk better than an off-the-shelf bot. The AI that beats them belongs to firms like Citadel, and it isn't for sale.

  3. 03
    Information

    They have information you don't.

    Listings before they're announced, flow, team and market-maker knowledge. Real, and structurally unavailable to a downloaded strategy.

  4. 04
    Luck

    They got lucky on one coin that covered the rest.

    Crypto returns are lottery-shaped: a few coins carry it, most go to zero. One winner covers a book of losers, and that's who posts the screenshot.

The alpha source

We kill almost everything. Two things survived.

Out of everything we have tested, two edges survived a real out-of-sample holdout. We publish the proof that they exist and that they hold, never the mechanism, which is the only part worth protecting. Neither is a bot you could buy, and we show exactly why.

Phantom Edge

Real edge, institutional-cost only
Vault-event microstructure reversion
24,671 events

across which the link between order-book thinness and price reversion held perfectly, a flawless monotonic relationship

This is a quoting input, not a bot you could buy. Every measured effect (2.63 bps reversion at 60 minutes) sits below the retail cost to trade it, and it only crosses into profit at institutional fee tiers. It is capacity-bounded to thin-book assets. We show the exact economics below rather than imply a return.

Asia Range

On trial, sample too thin to bank
Session-liquidity breakout (BTC)
+0.188R

out-of-sample expectancy, with almost no decay from training, the lone survivor of a holdout that killed the same idea on every other asset

On just 19 out-of-sample trades, which is thin enough that it could still be noise, and we say so in our own notes. It has only ever been paper-traded, never run with real capital. We publish it as a survivor on trial, not a proven winner.

See the full proof and economics Proof, not product. The mechanism stays private.
Put us to work

Heard a strategy that “works”?

Send the bot or the video. We test it on the same data and publish what we find.

We read every one. The good ones become a published test. Contact is only used to reply, never added to a list. See our Privacy Policy.

Or get one a week

One kill a week. With the numbers.

When a strategy fails its test, the write-up goes out. No signals, no hype, leave whenever.

Free. About one email a week. No signals, no spam.