Brad J. Bailey

What Millennium, Citadel, and Point72 Have Taught the Industry We always appreciate when risk-aware structures are taken seriously, and the big multi-strategy platforms have proven that they work. Firms like Millennium, Citadel, and Point72 have shown that you can industrialize risk without killing edge. Their pod-based architecture and centralized risk frameworks have delivered consistently strong, low-volatility returns across cycles. Allocators notice. And rightly so. From our vantage point, there’s a lot to respect in this model: – Tight drawdown controls and intraday risk management make it structurally difficult for any one pod in futures, FX, options, or crypto to jeopardize the broader platform. – The modular setup means hundreds of PM-led teams can run in parallel, each with their own mandate and P&L, while tech, capital, and risk stay centralized. But inside that structure? The reality is very different. Your capital is rented, not owned. Your seat exists at the intersection of performance and fit. Mismanage risk or simply fall out of sync with the platform’s risk profile, and your capital can be cut. Quickly. Even top-performing PMs speak openly about how a few bad weeks can threaten their seat, not just their bonus. From ConfluenceGP’s perspective, the message is clear: Respect the structure. These models have raised the bar for what good risk management in liquid alternatives can look like. But don’t ignore the human reality. Behind every pod is a team operating in an environment of world-class support and genuine professional fragility. That’s why our conversations are never just about Sharpe and AUM. They’re about what the framework feels like when you’re the one running the book. Have you ever tried viewing your role as if you were managing your own pod? How did that perspective shift things? And remember: it’s not just about architecture, but about the people navigating it every day.

8

QLE Partnerships -Bill Gates’ TerraPower has signed a 10yr offtake for HALEU worth $3.5bn -Senator Rick Perry’s Fermi America has a JV with for HALEU at their 11GW Hypergrid Campus in Texas -NECSA in South Africa has an MOU for HALEU production -One 30 Seven under QLE will transform nuclear waste into revenue by accelerating beta decay from hundreds of years to seconds. ….and now the Trumps are investing. This is a humanity changing company and most savvy global operators get it.

20

SOFR futures saw a big build in open interest on Wednesday’s selloff, suggesting big new shorts across Whites and Reds, where open interest increased 77k and 86k respectively. Meanwhile, Greens, Blues and Golds posted modest builds, again consistent with new shorts. USTs posted relatively mixed changes in open interest given the moves. In the long end, a $2.2 mn DV01 cut in USZ5 was mostly offset by a $1.6 mn DV01 build in WN, while TU was the only other notable change, where a build of $1.5 mn DV01 is consistent with new shorts.

1

Citadel: Citadel AI Assistant is a new chatbot tool that has been trained on licensed third-party content, including transcripts, regulatory filings, brokerage research reports and the hedge fund's own investment strategies, Citadel CTO Umesh Subramanian said https://lnkd.in/dBYcURBq

2

On alpha estimation traps: "Conventional approaches may oversimplify risk exposures, rely narrowly defined benchmarks, omit relevant factors, and misattribute beta timing to alpha, resulting in biased estimates that conflate genuine skill with statistical artifacts or unaccounted systematic risk." https://lnkd.in/ey7wVhji

8

Regime models are a critical component of time series forecasting with non-stationary real-world problems. New work by Rebecca Killick and co-authors Thomas Grundy and Ivan Svetunkov tackles this in a novel and I believe very important manner. They are applying change point detection on the forecast errors of *any* predictive model to signal when that model may have passed through a regime change in the underlying inputs and may need to be refit, reevaluated, or discarded. I feel like this is going to be one of those very watershed papers that gets applied all over the place. Use the best predictive model you can, and monitor that model's output reliability with a neutral, transferrable change point model. Highly recommended open access read, with open source code!

36

4 Comments

#Antimony may be one of the most critical metal investors still underestimate - yet without it, modern defense systems and key industrial applications simply don’t function. As global supply tightens and Western dependence becomes a strategic vulnerability, high-grade projects in stable jurisdictions are moving from niche to necessity. The real opportunity lies not in what the market already understands, but in what it has yet to fully price in. The interview of Lyndsay Malchuk with Jim Atkinson, CEO of Antimony Resources Corp. (CSE: ATMY | FSE: K8J0 | OTCQB: ATMYF) covers it all!

6