A field guide to AI positions

Understanding in language models

Sources are over 18 months old.

Publication dates and source age

Sources counted: 3

Newest dated source: 2022-10-24

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

The dispute over whether producing suitable language also involves grasping what that language means. [1] [2]

Reference this explanation or suggest a correction

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

Limits & distinctions

Open question: what would distinguish robust understanding from a successful shortcut? Test unfamiliar situations, changed assumptions and failures, rather than judging fluency alone. [2]

Reference this explanation or suggest a correction

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

A fuller explanation

Bender and Koller argue that training only on patterns in language cannot teach the connection between words and what speakers mean. In a separate Othello board-game study, a model predicting moves learned information about the board's state. That finding concerns an internal representation, not proof of human-like understanding. [1] [3]

Reference this explanation or suggest a correction

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

How it relates to the map

This debate concerns what models do, not membership of a camp on the map. [2]

Reference this explanation or suggest a correction

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

Share this page

https://theaiatlas.org/ideas/understanding/

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

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

  2. 2. The Debate Over Understanding in AI’s Large Language Models

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2022-10-14

    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 full version 2 manuscript and arXiv submission history. First submitted October 14, 2022; the linked version 2 is dated October 27, 2022. Surveys competing accounts, benchmark shortcuts and open questions. Its model examples describe that period, not a current capability ranking.

  3. 3. Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2022-10-24

    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 and submission history. Reports board-state representations and interventions in a synthetic Othello task. This source alone does not establish human-like comprehension.

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