# Categorizing Variants of Goodhart's Law

## TL;DR

This paper clarifies different failure modes of Goodhart's Law, emphasizing their relevance in AI and policy, and aims to improve understanding of these optimization failures across various fields.

## Contribution

It expands on Garrabrant's identification of four mechanisms behind Goodhart's Law, providing clearer distinctions and explanations of how these failures occur.

## Key findings

- Identifies and clarifies four distinct mechanisms of Goodhart's Law
- Highlights the importance of understanding these failure modes in AI and policy
- Provides a framework for better diagnosing optimization failures

## Abstract

There are several distinct failure modes for overoptimization of systems on the basis of metrics. This occurs when a metric which can be used to improve a system is used to an extent that further optimization is ineffective or harmful, and is sometimes termed Goodhart's Law. This class of failure is often poorly understood, partly because terminology for discussing them is ambiguous, and partly because discussion using this ambiguous terminology ignores distinctions between different failure modes of this general type. This paper expands on an earlier discussion by Garrabrant, which notes there are "(at least) four different mechanisms" that relate to Goodhart's Law. This paper is intended to explore these mechanisms further, and specify more clearly how they occur. This discussion should be helpful in better understanding these types of failures in economic regulation, in public policy, in machine learning, and in Artificial Intelligence alignment. The importance of Goodhart effects depends on the amount of power directed towards optimizing the proxy, and so the increased optimization power offered by artificial intelligence makes it especially critical for that field.