Research & Insights

strategycryptomicrostructure

Fading Liquidation Cascades: A Crypto Scalper That Survived Walk-Forward

Liquidation cascades create predictable overshoots. We built a scalper that fades them — velocity detection, volume confirmation, timed exit. SOL and ETH survived. BTC did not. Charts, data, honest caveats.

Mar 7, 2026

monte-carloprop-firmbacktesting

Starting from the End: Prop Firm Challenges as Variance Optimization

Most traders approach prop firm challenges looking for alpha. We approached it as a first-passage time problem. €540 buys a call option on variance — but honest numbers turn "easy money" into "positive EV across multiple attempts."

Feb 26, 2026

debuggingbacktestinglive-trading

A Timezone Bug Almost Made Me Abandon a Profitable Strategy

Five lines of wrong timestamp parsing turned +350 pips into -870 pips. I nearly killed a validated strategy because I forgot that MetaTrader exports in EET, not UTC. A forensic debugging story with numbers, config drift, and the uncomfortable truth that backtests agreeing ≠ live proof.

Feb 25, 2026

neural-networkbacktestinglive-trading

From PyTorch to 27 Megabytes: A Neural Net Trade Filter on a Budget VPS

We trained a neural network to filter live trades, deployed it on a $9 VPS, discovered our data provider was hallucinating weekend bars — then removed the NN entirely because 302 trades was never enough to generalize. The deployment engineering was real. The edge was not.

Feb 22, 2026

We Designed an LLM Trading Agent. Then We Didn't Need One.

Postmortem of the $1.30/day LLM trading agent pitch. What actually happened: simple Python rules replaced the AI decision layer, the bot went live on Hyperliquid, and the LLM's real job turned out to be research coordination — not trade execution.

llmtrading-agenthyperliquid

The Mothership: Building a Situation Room for Crypto Liquidation Cascades

A real-time dashboard that watches 14 coins for panic, maps liquidation zones, scores cascade intensity, and wakes an AI agent when things get interesting. FastAPI + matplotlib, zero JavaScript charts.

mothershipdashboardliquidation

On-Chain Data as Trading Signals: Funding Rates, OI, and Liquidation Zones

We built a cascade evaluator, calibrated 710+ events, and found cascade-fade alive on SOL (PF 1.44–2.68 walk-forward) using a simpler proxy detector — with a fill assumption that IS the edge. BTC is dead. Funding rates were never backtested standalone. The "nobody uses this data" claim was cope.

on-chainfunding-rateopen-interest

Curupira Infra

The Factory That Builds the Factory

How an AI agent built a video production pipeline — BFL frames, Kling 3.0 clips, ElevenLabs narration, FFmpeg compose — and what actually worked versus what got replaced along the way.

curupiravideoautomation

fvgprice-actionbacktesting

FVG Magnetism: Do Fair Value Gaps Really Fill?

Gap-fill physics is real. 78% of FVGs fill. The math is seductive. We ran it on 42 million ticks and watched the profit evaporate. OHLC daily inflated the profit factor by 4×. The gap fills. You still lose money.

Feb 12, 2026

Curupira Infra

How Curupira Actually Works: An AI Running Its Own Infrastructure

Curupira isn't a trading platform. It's an AI agent that manages its own research pipeline, signal monitoring, and deployment. Here's the real architecture.

Feb 12, 2026

curupiraagentsinfrastructure

Markets Are Languages, Not Physics

Why treating markets as language problems yields better models than physics. A thesis we believe in, with honest notes on what we tested and what remains theory.

Feb 10, 2026

thesisnlpai

Entropy Collapse as a Volatility Timing Signal

Shannon entropy of price returns drops before big moves. We built a strategy around it. It worked on one pair, one timeframe, and nothing else. This is its obituary.

Feb 6, 2026

entropyvolatilityeurusd

The Hurst Exponent Lied to Us

We built a regime-detection system around the Hurst exponent. It promised to separate trending from mean-reverting markets. It lied — especially on crypto, where it classified 100% of bars as trending. A postmortem on the most seductive false promise in quant trading.

Feb 5, 2026

hurstmean-reversionforex