Claims › Concept · What a machine cannot be said to do
Agent model
Does predicting text require representing the mind that wrote it?
A model can carry partial representations of the intentions behind the text it was trained on without being an agent itself.
Linked concepts: Form–meaning gap · Epistemic self-classification
Where it sits
How its claims lean on each other
The claims
-
“Moreover, the current debate suggests a fascinating divergence in how to think about understanding in intelligent systems, in particular the contrast between mental models that rely on statistical correlations and those that rely on causal mechanisms.”
The dispute over machine understanding is not one question but two pictures of what understanding is: tracking statistical regularities, or holding a causal model of how things work. Naming the split explains why the two camps talk past each other.
Mitchell & Krakauer 2023 · p. 1 · used · weight 1.25 · presupposes C008 · open C007
-
“In the course of performing next-word prediction in context, current LMs sometimes infer approximate, partial representations of the beliefs, desires and intentions possessed by the agent that produced the context, and other agents mentioned within it.”
Predicting the next word can require the model to build a partial picture of what the writer believed and wanted. The claim is about representations inside the system, not about the system being someone.
Andreas 2022 · §1 Introduction, (C1) · contested · weight 1.5 · contests C008 · open C006