---
title: Divergence Alarm
slug: divergence-alarm
url: https://templeton.host/lexicon/divergence-alarm/
type: defined-term
inDefinedTermSet: https://templeton.host/lexicon
author: Andrew Templeton
---

# Divergence Alarm

## Definition

A scale-free statistic between the preference posterior and the reality posterior that rings when the two stop agreeing under continued optimization. Three estimators in increasing cost: Kendall-tau between ranks, regret of the preference winner under reality, and the slope-opposition trend where the proxy climbs while realized outcomes turn down.

## Why this term exists

Goodhart's law is unfalsifiable when there is only one number; you cannot detect the proxy being gamed unless something else exists to compare against. The alarm is the only thing that fires on reward hacking before it shows up in the P&L - because by the time it shows up in the P&L, the optimization has already converged on the wrong target.

## See also

- [Alignment Kernels](https://templeton.host/frameworks/alignment-kernels)
- [Drift Detector](https://templeton.host/lexicon/drift-detector)
- [Verification Trap](https://templeton.host/lexicon/verification-trap)

Canonical URL: https://templeton.host/lexicon/divergence-alarm/