Factored cognition / chain-of-thought

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

• Chain-of-thought promptingmethod0.819
  Technique by which LLMs generate intermediate reasoning steps before final output; used by ChatGPT o3.
• Cognitionconcept0.793
  Mental actions including sentience; can be achieved by different biological and non-biological substrates.
• Performative chain-of-thoughtconcept0.789
  Central concept: verbalized reasoning that occurs after the model has already internally settled on an answer, particularly on easier tasks.
• Chain-of-Thought (CoT)framework0.786
  A prompting technique that elicits intermediate reasoning steps before final answer inference in language models.
• Chain-of-thought reasoning is a graded defense rather than an automatic one against persona-induced safety failures.claim0.778
  Finding from Study 2 showing reasoning models remain vulnerable under both prompting and activation steering
• Unfaithful Chain-of-Thoughtconcept0.777
  Phenomenon where steering vector intervention causes model's final output to contradict its own explicitly honest reasoning conclusion
• beyond cognitionconcept0.766
  Alexander's thesis that wholeness and the fifteen properties are objectively real, not artifacts of cognition, and are fundamental to physics and biology.
• Deliberative alignment via chain-of-thoughtconcept0.762
  Mechanism in which reasoning models consult safety policies within their chain-of-thought before answering, documented for gpt-oss