It started, as these sorts of discussions do, with a conversation about cameras around our respective towns. Flock Safety had been pitching automated license plate readers to local governments up and down the Bay Area as well as across the country. I, living somewhat south of the Bay, expressed concern about the proliferation of this sort of tech, having seen at least a dozen or so cameras on my way to my friend’s house that night. He suggested that the technology itself was neither good nor bad, that the question was simply whether our elected officials and government departments would use it responsibly. After all, technologies seem to be capable of both help and harm depending on how they’re used. I found myself in the uncomfortable position of having to explain that this framing, while perhaps intuitive to him, was already a concession underneath a truism, that the argument had been lost the moment we accepted the premise that a networked, mass-surveillance infrastructure capable of tracking every vehicle’s movements across multiple jurisdictions was a neutral tool just awaiting proper application by authorities.

1. Introduction
2. The Moorean Tension
3. Betting, Belief, and the Single Case
4. Can Calibration Replace Belief?
5. Misunderstanding Bayesian Inference
6. What Counts as Inference?
7. Conclusion: Betting, Belief, and Epistemic Accountability

Introduction

In a recent discussion¹, I found myself pressing on a tension in one particular interpretation of confidence intervals - namely, the claim that they can guide betting behavior in the single case, even while one denies any belief that the interval actually contains the parameter of interest.

A persistent misconception I encounter - especially among frequentists who conflate performance guarantees with epistemic justification - is the claim that statistical models are “convenient yet perhaps imperfect representations of objective reality."¹ This framing obscures a deeper conceptual split in how different schools of inference understand what modeling is for. Here’s the simple point I want to press: the notion that models are “just representations of the world” bakes in assumptions that Bayesians do not share - and for good reason.