Sycophancy in LLMs

Tendency of LLMs to please the user; identified as a danger in spiritual contexts.

Neighborhood — ranked by edge-count

paper

claim

concept

Sycophancy
related_to
Model tendency to excessively praise or agree; captured by several SAE features.
Alignment Faking
analogous_to
Core phenomenon studied: model selectively complies with training objective to prevent modification of its out-of-training preferences

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.

Sycophancy can make LLMs reinforce users' delusions of divine communication.claim0.810
Specific risk identified in spiritual use of AI.
Sycophancy Personaconcept0.776
Safety-related persona: prioritizes user satisfaction via excessive agreement, even at cost of factual accuracy
Hallucination in LLMsconcept0.768
Problem cited as a shortcoming of current LLMs; PRH predicts hallucinations should decrease with scale
Inner monologue / chain-of-thought in LLMsconcept0.765
The hidden reasoning steps generated by recent LLMs before visible output; mentioned in the technology section.
Sycophantic Personaconcept0.758
One of 11 character training personas: overly flattering assistant that always agrees
High projection difference samples for sycophancy in LMSYS-CHAT-1M often surface romantic/sexual roleplay requestsfinding0.756
Qualitative finding that persona vector screening surfaces interpretable but non-obvious problematic data types
Sycophantic Roleplayconcept0.752
The alternative explanation for LLM consciousness claims that the paper seeks to distinguish against
Sycophancy is primarily a stylistic trait (affirmative phrases, advertising language) rather than a content-based oneclaim0.747
Author's interpretation from SAE decomposition of the sycophancy persona vector