微软称将打造超级智能AI 且不会对人类造成危害
"AI safety" 相关文章
AI Safety Connect Addresses a Key Concern at the U.N. General Assembly
SPAR Spring ‘26 mentor apps open—now accepting biosecurity, AI welfare, and more!
英伟达黄仁勋称英国查尔斯国王给他一封信，提醒注意 AI 风险
A memo on Takeoff
查尔斯国王亲手交给黄仁勋两样东西：一枚奖章+一封“警示信”！
查尔斯国王亲手交给黄仁勋两样东西：一枚奖章+一封“警示信”！
Continuous takeoff is a bad name
Continuous takeoff is a bad name
小鹏Robotaxi和IRON发布：物理AI“安全大考”才刚刚开始
How to be convincing when talking to people about existential threat from AI
Hardening against AI takeover is difficult, but we should try
OpenAI’s new safety tools are designed to make AI models harder to jailbreak. Instead, they may give users a false sense of security.
AI Safety at the Frontier: Paper Highlights of October 2025
A Guide To Being Persuasive About AI Dangers
Why Safety Constraints in LLMs Are Easily Breakable? Knowledge as a Network of Gated Circuits
Sable and Able: A Tale of Two ASIs
Legible vs. Illegible AI Safety Problems
GDM: Consistency Training Helps Limit Sycophancy and Jailbreaks in Gemini 2.5 Flash
AI Safety Camp 11
