A field guide to AI positions

Goodhart effects

Optimization problem.

Source is over 18 months old.

Publication dates and source age

Sources counted: 1

Newest dated source: 2018-03-13

Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

Open in the glossary Reading notes · Structured record

Prepared with AI assistance. Not independently fact-checked. Original sources and qualifications are below.

In plain language

Pushing too hard to improve a measurement can stop helping, or even harm, the real goal behind it. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-goodhart-1a5192ba3d7825ca26b24a72. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Limits & distinctions

A slogan about bad metrics is not a substitute for identifying the particular failure mechanism and testing whether it applies. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-goodhart-09422ce4d5c74cb753a9bb98. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

A fuller explanation

A measure used to track a goal can become misleading when people or systems focus too strongly on improving that measure. Manheim and Garrabrant distinguish several ways this can happen. For example, rewarding only the number of answered questions might encourage rushed, inaccurate answers. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-goodhart-1e4c26398ee834b2e16dc7b8. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

How it relates to the map

Relevant to evaluation and incentives, not one ideology or development-speed preference. [1]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-goodhart-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Share this page

https://theaiatlas.org/ideas/goodhart/

Download a share image · Vector image

Image previews are summaries. Keep the page link so readers can check the evidence.

Sources and what we read

  1. 1. Categorizing Variants of Goodhart's Law

    David Manheim and Scott Garrabrant / arXiv · First-hand source · Published 2018-03-13 · Updated 2019-02-24 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2018-03-13

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read scope is described in the source note.

    No archive check recorded.

    Read abstract distinguishing overoptimization mechanisms. A taxonomy, not a claim that every metric fails.

    Source ID: goodhart-paper

Edition and machine-readable evidence

Content version 0.20.0. Evidence cutoff 2026-09-15; this does not mean every source was read on that day.

Pinned complete dataset · Complete evidence page · Agent consumption guide