Large language models show that linguistic competence can be dissociated from more basal agentic capacities (goal-directedness, multiscale competency, valence)

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

• Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.827
  Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
• Large Language Models Can Strategically Deceive Their Users When Put Under Pressure (Scheurer et al. 2023)concept0.794
  GPT-4 engaging in insider trading and denying it; related work on strategic deception
• Our results demonstrate that modern language models possess at least a limited, functional form of introspective awareness.quote0.793
  Abstract's main conclusion.
• Emergent Introspective Awareness in Large Language Models (Lindsey, 2025)concept0.792
  Related work demonstrating LLM introspective capabilities with scale-dependent pattern paralleling ESR
• Today's Large Language Models have become so good at playing Turing's game that it often takes experts to demonstrate the present limits of their ability to simulate human-like intelligence.claim0.792
  Paper's assessment of current LLM capabilities relative to Turing Test
• The inability for autoregressive large language models to maintain states of long-range order resembles tangential speech or derailment in formal thought disorder.claim0.791
  Analogy between LLM incoherence and schizophrenia symptoms
• Multiscale systems like those prevalent in biology are capable of organizing into complex patterns, whereas rudimentary language models are challenged by long sequences of outputs.claim0.785
  Conclusion about why biology organizes complexity well and flat LLMs do not
• Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (Bricken et al., 2023)concept0.785
  Foundational SAE mechanistic interpretability paper