A field guide to AI positions

Mesa-optimization & inner alignment

Research concept.

Source is over 18 months old.

Publication dates and source age

Sources counted: 1

Newest dated source: 2019-06-05

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 possibility that a trained AI pursues its own internal objective, which may differ from its training objective. [1]

Reference this explanation or suggest a correction

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

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

Limits & distinctions

The paper analyzes when this might occur. It does not establish that every neural network is an optimizer or is secretly pursuing a hidden goal. [1]

Reference this explanation or suggest a correction

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

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

A fuller explanation

Training can produce a model that itself searches for ways to achieve a goal. Researchers call this mesa-optimization. If the goal it pursues differs from what the training process rewarded, that creates an inner-alignment problem. [1]

Reference this explanation or suggest a correction

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

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

How it relates to the map

A proposed failure mechanism relevant to safety research, not a measured chance of catastrophe. [1]

Reference this explanation or suggest a correction

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

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

Share this page

https://theaiatlas.org/ideas/mesa/

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. Risks from Learned Optimization in Advanced Machine Learning Systems

    Evan Hubinger and coauthors / arXiv · First-hand source · Published 2019-06-05 · Updated 2021-12-01 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2019-06-05

    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 revision history introducing mesa-optimization and the relation between learned and training objectives.

    Source ID: learned-optimization

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