Towards safety cases for frontier AI training
中文摘要
前沿AI训练安全案例指南涵盖技术防护、运营实践及对齐失效事件调查。
English Summary
Guidelines for frontier AI training safety cases cover technical safeguards, operational practices, and investigations into misalignment incidents.
原文节选
Our early guidelines for safety cases in frontier AI training cover technical safeguards, operational practices, and investigating misalignment incidents