Someone asked me recently whether strategies based on mean reversion, trend following, and momentum are “good” or just data mining. It’s a reasonable question, but it reveals some confusion that arises from mixing up two things that sound similar but are very different. Mean reversion, trend, momentum: these aren’t edges. They’re labels for how prices ...

My last two articles on AI and trading research got more engagement than almost anything I’ve written. “More of the Disease, Faster” argued that LLMs can’t answer the critical question: who pays you and why? “AI Will Create Millions of Quants” went deeper on the why: AI makes beautiful backtests trivially easy to produce, which means ...

(Most of Them Will Lose Money) AI makes it easier than ever to build trading strategies. Prompt a model, run a backtest, optimise some parameters, and suddenly you’ve got a beautiful equity curve staring back at you. It feels like progress. It feels like research. I wrote recently about how AI coding assistants tend to ...

This week I discovered the “vibe quant” movement (or rather, it discovered me). People using LLMs to find trading strategies, validate them, and put them into production. The pitch is seductive: the LLM reads the literature, implements the ideas, backtests them, and you just supervise. I think this approach is going to cost people a ...