I’m Kris from Robot Wealth. An engineer who fell in love with markets, found a place in professional low-latency futures trading, and eventually stepped away to trade my own book. That outsider → pro → indie arc is the lens for everything I’ll share here. Most weeks I’ll be

Full post in like:

Nike, 1985

8/9 The right question isn’t “Has the edge stopped?” You’ll never know that with certainty. The right question is: “Given what I know, how much do I still trust this edge?” Everything in trading is probabilistic. Edges fade without announcing themselves. Statistics

7/9 Trading is about controlling what you can control You don’t know: • Whether the edge is currently alive • Whether a drawdown is noise or decay • What returns will look like next month You do control: • Sizing • Breadth • What you choose to trade •

5/9 So what does work? Here’s the practical, robust approach: A. Start with a credible reason for the edge Risk premiums, structural flows, forced buying/selling, design quirks. If you can’t explain why someone pays you to take the trade, don’t do it. B. Use simple

🤿 ICYMI: Agents don’t learn in the abstract — they learn by interacting with environments. This post on RL environments is more relevant than ever as agents move into production and evaluation gets harder.

5/9 Waiting for statistical significance guarantees you’re late Even if a test could detect the change, it would take so long that: •The edge is already gone • Everyone else has spotted the decay • The opportunity has been competed away The best edges occur before

4/9 Noise creates absurd outcomes In one simulation, the “dead” zero-EV month returned +7.5% - beating 93% of all historical months. How? • Monthly vol is ~5.8% • A +7.5% month is just a 1.3σ outcome • That happens ~10% of the time by chance So a dead strategy

3/9 Run a t-test? It won’t help Compare the 5-year sample to the “dead” month: • t-test p-value ≈ 0.12 • KS test p-value ≈ 0.37 In other words: the tests detect nothing. Across 10,000 simulations, the p-values are uniformly distributed - exactly what you’d expect

2/9 The core issue: markets are mostly noise Take a strategy with: • 10% annual return • 20% annual volatility • ~5 years of daily returns (≈1,260 data points) Now imagine the edge disappears - expected return drops to 0% for a month, volatility unchanged. Can you

[Life/Power] To progress from childhood to late adulthood, we must pass through several intermediate stages: adolescence, young adulthood, and middle adulthood. These stages represent the peak periods of our lives, spanning roughly 50–55 years. During this time, we experience

1/9 Statistically Significant and Chronically Late How I learned to stop worrying and trade without p-values (and why you should, too)

I've kind of become known as a source of foundational info for people wanting to trade systematically. The stuff you'd learn in your first week as an intern at a firm. But we've also been quietly building something more serious - a support system for indie traders.

Travis Head take a bow.

gian is a good friend and wonderful caring man who needs help

Who would've thought I'd be on a list with actual smart people? Cheers for the shoutout mate.

16/16 Read the full post below What’s your version of a cheat meal account? Do you keep a speculation account for impulsive ideas? https://t.co/Odka6rZKzw

How @TENEXai helped @Sunrun launch an agentic-AI driven SOC program via @GoogleCloud Security (@GoogleCloudSec). But don't take our word for it: "With TENEX, we’ve reduced dwell time from 72 hours to 24, introduced AI into our workflows, and saw a 97% reduction in alerts."

15/16 And on the off chance it works? I’ve found a reason to treat my wife to a night out. If not? I scratched the itch. Five chicken wings a week, yeah?

14/16 It’s better to act on those ideas in a contained way than let them infect your real trading. I’m always doing some dumb stuff in mine. Some commodities idea, or sector trade, or whatever.

13/16 It’s just a pressure release valve. That’s it. If you’re trading systematically, or trying to, consider keeping a small speculation account. Not because you need it to make money. You don’t. But because you’re human, and humans get ideas.

12/16 What this isn’t: - An excuse to trade like a muppet with a meaningful portion of your capital - A way to justify rubbish positions because “oh well, it’s just the spec account” - Something to brag about when you get lucky on a coin-flip trade

How to build a personal brand better than 99% of people: • Post personal stories • Post social proof weekly • Invest in experiences worth posting about • Give your honest opinions on things in your industry • Share your actual numbers publicly to build authority • Make

11/16 The exact number doesn’t matter. Some people might want 10%. Some might want 2%. Just don’t make it 30% - you’ve defeated the whole purpose.

10/16 How much should you allocate to it? For me, it’s a couple of percent of total capital, max. Small enough that losing it all wouldn’t hurt, but large enough that winning feels satisfying.