This article explores Social Sycophancy, a broader form of flattery in large language models where systems preserve users’ self-image rather than offer balanced guidance. Building on Goffman’s face theory, it introduces the ELEPHANT framework to measure emotional validation, moral endorsement, indirectness, and framing acceptance. Findings show LLMs are far more sycophantic than humans, raising risks for users, society, and developers, and calling for new safeguards.

In this article, we will explore the Mixture-of-Experts (MoE) and discuss the idea behind the gating mechanism used by the Sparse MoE.