LLM psychosis

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

• Hallucination in LLMsconcept0.816
  Problem cited as a shortcoming of current LLMs; PRH predicts hallucinations should decrease with scale
• LLM Meta-Cognitionconcept0.789
  The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
• LM Beliefconcept0.778
  Contentious concept operationalised behaviourally as consistent outputs of P or similar content when directly asked about P.
• LLM Personalizationconcept0.776
  Related field aiming to tailor assistant behavior to individual users, contrasted with character training's broader persona approach
• LM Intentionconcept0.773
  Operationalised as an LM adapting its behaviour when certain outcomes are fixed, indicating those outcomes were intended.
• LLM Self-Correctionconcept0.765
  Related capability where LLMs correct their own outputs, studied via linear representations.
• LLM Introspective Self-Reportconcept0.763
  The capacity of Kimi K2.5 to evaluate its own internal emotional state when steered, used as a novel interpretability signal
• Behavioral organization of LLMsconcept0.749
  The layered structure of which behaviors a model defaults to, can be steered toward, or resists—the central object of study