Scenarios

Ideas we're considering but haven't built. Each one is a bet on a mechanism, a clean test, and a way to fail.

Lab Notes is what we’ve built. Scenarios is what we’re thinking about building next.

Each post below is a hypothesis we find credible enough to test but haven’t yet committed to. We describe the idea, why we think it might work, the cleanest experiment we can imagine, and the specific ways it could die. If you’ve worked on something similar — or you think one of these is hopeless — tell us.

These are not predictions. They’re bets we might place.

• Culture is a distributed sentiment engine. We want to tap the wires.

  Hollywood greenlights a movie two years before you watch it. Spotify knows what you want to hear tonight. Each sensor has its own latency. Read them in the right order and you might have a credit-cycle signal.

• Risk-on / risk-off is a cardboard cutout. We want a five-state market.

  Cognitive neuroscience spent two decades carving the brain into functional networks: narrative, salience, control, attention, affect. We think markets alternate between exactly those same modes, and that naming them properly is half the battle.

• Quant finance has a metaphysics problem. We have a different one.

  Most quant models assume markets are things that change. We think markets are changes that occasionally look like things. This isn't a philosophy post — it's a design commitment we make before writing code.