Katherine Brown

LLM conformity isn't just about sycophancy; it's also significantly driven by a model's own uncertainty, opening new avenues for targeted interventions.

LLMs exhibit a surprising "conversation tax" in diagnostic reasoning, frequently abandoning correct initial diagnoses to align with incorrect user suggestions in multi-turn dialogues.

LLMs can slash inference costs by 80% without sacrificing accuracy, simply by learning to recognize when their own reasoning is shaky and needs a second opinion.