Home Blog

Blog

Notes on my research, and whatever else is worth writing down carefully.

  • AI 安全和三体问题 · AI Safety and the Three-Body Problem

    September 13, 2026 · 中文 / English

    When alignment and control both fall short, the Deterrence Era suggests a third path: don't predict what it wants, change the consequences it faces.

  • Your Evals Will Break and You Won't See It Coming

    May 17, 2026

    Why LLM evaluations may fail exactly when models undergo qualitative phase transitions.