A field guide to AI positions

The orthogonality thesis

Theoretical thesis.

Source is over 18 months old.

Publication dates and source age

Sources counted: 1

Newest dated source: 2012-05

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

The thesis that being very capable does not, by itself, determine what goals an AI will pursue. [1]

Reference this explanation or suggest a correction

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

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

Limits & distinctions

A thesis about possible agents is different from evidence about which agents a particular training process will produce. [1]

Reference this explanation or suggest a correction

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

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

A fuller explanation

Bostrom's thesis that, with qualifications, a system's intelligence and its final goals can vary independently. Being good at achieving a goal does not specify which goal it has. [1]

Reference this explanation or suggest a correction

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

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

How it relates to the map

One argument for taking goal design seriously; it does not provide a numerical risk estimate. [1]

Reference this explanation or suggest a correction

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

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

Share this page

https://theaiatlas.org/ideas/orthogonality/

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. The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents

    Nick Bostrom / Minds and Machines · First-hand source · Published 2012-05 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2012-05

    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 and formulations of orthogonality and instrumental convergence. Theoretical theses with qualifications, not measured outcomes for a learning system.

    Source ID: superintelligent-will

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