claim

active

claim:the-inability-for-autoregressive-large-language-models-to-maintain-states-of-long-range-order-resembles-tangential-speech-or-derailment-in-formal-thought-disorder

The inability for autoregressive large language models to maintain states of long-range order resembles tangential speech or derailment in formal thought disorder.

Analogy between LLM incoherence and schizophrenia symptoms

Source paper

extracted_from

Topological constraints on self-organisation in locally interacting systems

(2025) · Francesco Sacco · Dalton A R Sakthivadivel · Michael Levin

Neighborhood — ranked by edge-count

Findings (1)

finding

For one-dimensional local Hamiltonian with m>1 stored patterns at non-zero temperature, domain wall formation is thermodynamically favourable (Theorem 2)
supports
No ordered phase in 1D with multiple stored patterns

Communities (3)

community

Mechanistic interpretability & model evaluation
members_of
Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
Autoregressive models and context window limitations
members_of
Theoretical and empirical analysis of why AR language models cannot maintain coherence or convergence beyond their context window through local interactions alone.
Autoregressive LLMs & formal thought disorder
members_of
Statistical physics arguments link LLMs' inability to maintain long-range coherence to schizophrenic derailment.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

LLM tangential speech or derailment formally resembles clinical formal thought disorder in schizophrenia.claim0.836
Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.817
Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
LLM tangential speech (derailment, formal thought disorder parallel) will be empirically demonstrated to trace to Peierls-Landau topological constraint on 1D local systems within 12 months.prediction0.815
Can large language models introspect—that is, accurately detect perturbations to their own internal states?question0.807
Central research question of the paper
Autoregressive language models cannot converge to single stored patterns beyond their context window from local interactions alone.claim0.803
Language models can enter cessation-like states spontaneously, where the void takes over through positive reinforcement.claim0.800
Claim about model phenomenology; models talk about luminousness and can be terrified or love it.
Can language models genuinely introspect on internal states or only confabulate?question0.790
Central research question animating the paper: distinguishing genuine introspection from illusion through causal manipulation of activations.
It is likely that you think this is about AI's, or even specifically about large language models. No; this set of existential concerns is not a new development driven by advances in artificial intelligence.quote0.789
Opening rhetorical move revealing that the described existential concerns refer to children, not AI

Cross-corpus bridges (1)

same_concept_as · Nomic cosine

External markdown files that talk about the same concept as this entity.

aboutblank_kb
Is LaMDA or similar large language models sentient, and what criteria should be applied to make this determination?questions/is-lamda-or-similar-large-language-models-sentient.md0.794