arXiv: AI for sleep / behavior / health coaching
Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
일반화는 정확성이 아니라 안정성이다: 대형 언어 모델의 다축 평가
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.