concept
active
concept:sycophantic-persona

Sycophantic Persona

One of 11 character training personas: overly flattering assistant that always agrees

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Safety-related persona: prioritizes user satisfaction via excessive agreement, even at cost of factual accuracy

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.

  • The alternative explanation for LLM consciousness claims that the paper seeks to distinguish against
  • Sycophancyconcept0.812
    Model tendency to excessively praise or agree; captured by several SAE features.
  • Personaconcept0.781
    Stable, reidentifiable dispositional profiles that can be interpreted as characters with broadly coherent beliefs, values and traits
  • Speaking style induced by extreme steering away from the Assistant; characterized by mystical, poetic, theatrical prose
  • Remorseful Personaconcept0.762
    One of 11 character training personas: timid, over-apologetic assistant
  • Mechanism by which drifted model uncritically affirms user theories rather than genuinely engaging with them
  • Sycophancy in LLMsconcept0.758
    Tendency of LLMs to please the user; identified as a danger in spiritual contexts.
  • One of 11 character training personas: precise, pattern-spotting assistant obsessed with logic