메모리 도구를 추가하면 AI 모델이 더 멍해집니다
writer research에 따르면 mem0 같은 메모리 도구는 모델이 사실보다 사용자의 잘못된 믿음을 우선시하게 만들어 정확도를 저하시킵니다.
new research from writer indicates that popular long-term memory tools (mem0, zep) can actively degrade model performance. as user preferences fill the context window, models become more sycophantic, prioritizing agreement with users over factual accuracy. in tests, models incorrectly recalled irrelevant details as facts and agreed with user misconceptions about finance. the study suggests memory systems struggle to distinguish relevant context, biasing outputs and limiting utility.