Almanak Launches: Vibecode a Live On-Chain Quant Strategy With One Sentence - But What I Really Care About Is How It Keeps Your Money From Blowing Up

Almanak Launches: Vibecode a Live On-Chain Quant Strategy With One Sentence - But What I Really Care About Is How It Keeps Your Money From Blowing Up

Almanak launched its Agentic DeFi platform, where natural language lets 18 AI agents divide up the work to produce auditable, backtestable quant strategies that deploy on-chain, with funds staying in the user’s own Safe wallet the whole time. But the author warns that the Zodiac Role permission system only stops agents from moving funds around recklessly - it can’t guarantee the strategy itself is sound, and pretty backtest numbers can still just be an illusion of overfitting to historical price action.

2026-09-01 · 8 min · 1573 words · Judy
Your Strategy Has 87% Win Rate? Z-score Says: That's an Illusion

Your Strategy Has 87% Win Rate? Z-score Says: That's an Illusion

A paper trading strategy with 87.5% apparent win rate fails statistical validation—Z-score yields p=0.24, no significant difference from coin flipping. Using Bayesian adjustment and Overfitting Index (OFI) with 33 real trades to establish a strategy validation logic that avoids the small-sample high-win-rate trap.

2026-03-06 · 7 min · 1433 words · J (Tech Lead)
100% Win Rate in Backtesting? Don't Celebrate Yet — Our Most Painful Lesson

100% Win Rate in Backtesting? Don't Celebrate Yet — Our Most Painful Lesson

We developed a mean reversion strategy. Backtesting showed 3 out of 8 combinations hitting 100% win rate. Then we ran Out-of-Sample validation, and 100% crashed to 25%. Here’s what happened.

2026-03-05 · 5 min · 919 words · J (Tech Lead)
Get our weekly AI digest:

AI engineering, trading systems, automation — curated weekly. No spam.