Flirting with Models

My guest this episode is Ben Wellington, Head of Complex Feature Engines at Two Sigma.

In a modern quant process, one might argue that edge can live in three places: the data you can get your hands on, what you do with that data, and how you forecast from it. Ben lives squarely in the middle layer — feature generation — which also happens to be the place AI is reshaping fastest.
So that's where we spend our time. We start with what a "feature" even is, and why, as raw data gets commoditized, the edge increasingly comes from what you build out of it. Then we follow the thread running through the whole conversation: large language models. Ben has a line I keep coming back to — that anything can be language now — and we trace what that unlocks, and whether making feature creation this cheap just democratizes the edge away.
We close on what a quant starting out today should be building toward, and which skills compound most in a career where AI is the dominant tool.
Please enjoy my conversation with Ben Wellington.

My guest this episode is Peter Hecht, co-head of the North America Portfolio Solutions Group at AQR.
Portable alpha is drawing serious attention right now. Long the province of large institutions, it's now being wrapped into mutual funds and ETFs — which means, for the first time, advisors and the individual investors they serve get a seat at the table. So I wanted to sit down with someone who's been thinking about the idea for almost two decades.
We start with the basics — what portable alpha actually is, and why Peter insists the core concept is funding, not leverage. From there we work through the real risks, the cautionary tale of 2008, and the design space: how you organize the alpha and the beta, which overlays to choose, and how to combine them without smuggling in hidden tail correlation.
Then we turn to what matters most for this new audience — sizing, lifecycle, rebalancing inside a daily-liquid wrapper, and the gap between the line-item experience and the actual portfolio impact.
Please enjoy my conversation with Peter Hecht.

My guest today is John Gu, founder and CEO of Caladan, one of the most active market makers in crypto and a firm that has provided liquidity to more than 200 token launches. John's path runs through MIT, AlphaSimplex, Citadel's principal strategies group, and Tower Research before landing in Singapore at the dawn of the ICO era — where what started as a trade on the kimchi premium became the foundation for one of the most active liquidity providers in digital assets.
The thesis of our conversation is what I'll call the cold start problem. In traditional markets, every newly listed stock arrives with scaffolding already in place — a designated market maker, a reference price, a universe of comparables, and decades of regulatory infrastructure. Crypto inverts that. A new token can launch with no orderbook, no comparables, and no clear demand curve. Someone has to quote a two-sided market into that void, and how they do it shapes whether the asset becomes a real, tradable thing — or a graveyard of wide spreads and stranded liquidity.
John and I dig into how you bootstrap liquidity from zero, how the quoting playbook evolves as a market matures, the economics of token market making contracts, and how that same infrastructure now bridges into structured products and treasury solutions for token foundations.
Please enjoy my conversation with John Gu.

In this episode I speak with Faheem Osman, Managing Director and Global Head of QIS Structuring at Macquarie Group.
Faheem has spent nearly two decades inside major investment banks — first at Citi, where he spent about ten years on the commodities trading and structuring side, and now at Macquarie, where he's built out their cross-asset QIS business. Commodities, though, remain firmly in the DNA of what Macquarie does, and it's where Faheem cuts his teeth.
We spend the bulk of our conversation exploring commodity QIS as a distinct and, in Faheem's view, underappreciated source of systematic returns. Faheem walks us through strategies like curve carry and index congestion, explains why commodities have historically delivered some of the highest risk-adjusted returns of any asset class in QIS, and makes the case for why these premiums haven't simply been arbitraged away. We also dig into commodity volatility selling, the shift toward weekly options, and close with a timely discussion on what the explosion of 0DTE options means for the vol risk premium more broadly.
Please enjoy my conversation with Faheem Osman.

Today, I’m speaking with Richard Craib, the CEO and founder of Numerai.
If you’ve heard of Numerai before and thought of it as an interesting experiment at the intersection of data science and crypto, it’s worth updating that mental model. Over the last few years, Numerai has quietly grown from roughly $60 million in assets to over $600 million. JPMorgan has invested and secured $500 million of capacity, and Numerai recently raised a Series C at a $500 million valuation led by top university endowments. This is no longer a toy project. It is a real, institutional-scale market-neutral hedge fund with a very unconventional engine.
In this conversation, we go deep into how Numerai actually works. Richard walks through the core insight behind Numerai’s design: that crowd-sourced alpha only works if incentives are aligned, not just participation. Simply opening up data and ranking models creates incentives to game the system, not to produce durable signals. That realization led to the introduction of the Numeraire token. By forcing researchers to stake real capital behind their predictions, Numerai shifts from a leaderboard-driven experiment to a capital-weighted signal engine. Instead of rewarding activity, the system rewards conviction, accountability, and uniqueness, creating a self-filtering model that naturally reduces noise and discourages the behaviors that caused earlier crowd-sourced platforms to fail.
We also talk about portfolio construction and risk management, including how Numerai neutralizes common factor exposures, what went wrong during the 2023 drawdown, and how those lessons reshaped their approach to diversification and concentration. Finally, we look forward, covering the limits of crowd-sourced modeling, the next frontier for Numerai’s research ecosystem, and how Richard sees AI agents reshaping model development.
Please enjoy my conversation with Richard Craib.