concept
active
concept:factored-cognition-chain-of-thoughtFactored cognition / chain-of-thought
Using multi-step reasoning by generating intermediate thoughts.
Neighborhood — ranked by edge-count
Concepts (2)
concept
- Chain-of-Thought Reasoningrelated_toMedium through which eval awareness is often verbalized; target of intervention.
- chain-of-thoughtrelated_toA technique that outputs intermediate reasoning steps, used here to detect verbalized eval awareness.
Hypotheses (1)
hypothesis
- About chain-of-thought and process safety.
Artifacts (1)
artifact
- Simulators (LessWrong post)mentionsThe paper being extracted.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Technique by which LLMs generate intermediate reasoning steps before final output; used by ChatGPT o3.
- Behavior-based explanation that is not fully faithful.
- Monitoring reasoning traces for misbehavior.
- Whether written reasoning reflects actual model mechanisms.
- Mental actions including sentience; can be achieved by different biological and non-biological substrates.
- Central concept: verbalized reasoning that occurs after the model has already internally settled on an answer, particularly on easier tasks.
- A prompting technique that elicits intermediate reasoning steps before final answer inference in language models.
- Finding from Study 2 showing reasoning models remain vulnerable under both prompting and activation steering