A field guide to AI positions

Self-supervised learning

Inside a model.

Sources are over 18 months old.

Publication dates and source age

Sources counted: 2

Newest dated source: 2021-03-04

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

Training that builds its target answers from the data itself, such as a hidden word. [1]

Reference this explanation or suggest a correction

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

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

Limits & distinctions

The original text supplies a target, not independent proof that its claims are true. Self-supervised does not mean self-verifying. [1] [2]

Reference this explanation or suggest a correction

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

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

A fuller explanation

Software can hide part of a text, ask the model to predict it and compare the prediction with the original. This supplies a training signal without someone labeling each example separately. [1]

Reference this explanation or suggest a correction

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

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

How it relates to the map

Read this alongside pretraining to see where a language model’s practice targets come from. [1]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-self-supervised-learning-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

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

Share this page

https://theaiatlas.org/ideas/self-supervised-learning/

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. Self-supervised learning: The dark matter of intelligence

    Yann LeCun and Ishan Misra / Meta AI · First-hand source · Published 2021-03-04 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2021-03-04

    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 the predictive-learning section and text masking examples. Used for how targets are formed. The authors’ forecasts about common sense and human-level intelligence are not adopted.

    Source ID: glossary-model-self-supervised

  2. 2. Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data

    Emily M. Bender and Alexander Koller / ACL · First-hand source · Published 2020-07 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2020-07

    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 the paper and abstract. A position argument about meaning learned from form alone, not an experimental verdict on every multimodal or tool-connected system.

    Source ID: understanding-bender-koller

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