Rowan Wang: Alignment in Frontier AI Models
An Anthropic research talk on alignment in frontier AI models｜Anthropic 研究員分享前沿 AI 模型的 alignment 研究。
Registration｜報名: Sign-up form｜報名表單 | LinkedIn Post: Event announcement
About the Talk｜活動簡介
NTU AI Safety is excited to welcome Rowan Wang, a researcher on Anthropic’s Alignment team, for a talk on the AI safety topics he is most interested in and Anthropic’s latest research on model alignment and model self-improvement.
Participants can submit questions for Rowan in advance and discuss alignment training, model auditing, and automated alignment research during the event. The talk will be conducted entirely in English.
NTU AI Safety 將邀請 Anthropic Alignment 團隊研究員 Rowan Wang，分享他目前最關注的 AI Safety 議題，以及 Anthropic 在 Model Alignment 與 Model Self-Improvement 方面的最新研究。
參與者可在報名時預先提交問題，並於活動中進一步交流 alignment training、model auditing 與 automated alignment research 等主題。本場講座將全程以英文進行。
Speaker｜講者
Rowan Wang is a researcher on Alignment at Anthropic. His research has focused on alignment training, model auditing, and automated alignment research. Before joining Anthropic, he studied Computer Science and Statistics at Harvard University.
Rowan Wang 是 Anthropic Alignment 團隊的研究員，研究重點包括 alignment training、model auditing 與 automated alignment research。加入 Anthropic 之前，他曾於哈佛大學修讀電腦科學與統計學。
Topics｜分享內容
- Current research interests in AI safety｜目前關注的 AI Safety 研究議題
- Alignment in frontier AI models｜Frontier AI models 的 alignment
- Model self-improvement and automated alignment research｜Model self-improvement 與 automated alignment research
- Model auditing｜Model auditing
- Participant Q&A｜參與者問答
Event Details｜活動資訊
- Date｜日期: July 13, 2026 (Monday)｜2026 年 7 月 13 日（一）
- Time｜時間: 12:00 PM (UTC+8)
- Language｜語言: English｜英文
- Format｜形式: Online; the meeting link will be sent to registered participants two days before the event｜線上；會議連結將於活動前兩天寄送給完成報名者
- Registration deadline｜報名截止: July 10, 2026 at 11:59 PM｜2026 年 7 月 10 日晚上 11:59