链接
研究重点
Adversarial Robustness and Safeguards, Misalignment Science, Alignment Training Methods, Interpretability, Theoretical Alignment and Formal Methods
Gabriel Wu 是 OpenAI 的 AI 对齐研究员。此前，他在 Harvard 负责AI Safety Student Team，并在 Harvard 获得计算机科学硕士学位和数学学士学位。