A field guide to AI positions

AI safety & alignment

Publication dates and source age

Sources counted: 3

Newest dated source: 2025-09-22

At least one source was published within the 18-month window.

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

In plain language

Research aimed at reducing AI harms and improving reliability and alignment with intended goals. A safety goal or framework is not proof that a system is safe. [1] [2] [3]

Reference this explanation or suggest a correction

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

Limits & distinctions

A safety framework records stated safeguards, not a guarantee of safe implementation or a measured catastrophe probability. [3]

Reference this explanation or suggest a correction

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

A fuller explanation

Work on making AI systems behave safely and reliably. Alignment concerns how system behavior relates to intended goals and human values; catastrophic-risk reduction is one focus of safety work. [1] [2]

Reference this explanation or suggest a correction

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

How it relates to the map

Neither a single actor nor one required pace preference. Research, evaluation and governance can support different development policies. [1] [3]

Reference this explanation or suggest a correction

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

Share this page

https://theaiatlas.org/ideas/safety/

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. Concrete Problems in AI Safety

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2016-06-21

    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 the abstract's five accident-risk problems including reward hacking and distributional shift. Does not give a general catastrophe probability.

  2. 2. Risks from Learned Optimization in Advanced Machine Learning Systems

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

  3. 3. Strengthening our Frontier Safety Framework

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2025-09-22

    At least one source was published within the 18-month window.

    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.

    The article contains an April 2026 update. A published framework is evidence of stated policy, not an estimate of catastrophe probability.

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