Meta 发布 Muse Wonder 系列,主打对齐与安全能力
Meta 发了 Muse Wonder 系列,重点不在跑分而在安全和隐私处理,想看大厂怎么练防注入的可以看看。
Meta 在 X 上介绍了 Muse Wonder 模型家族的对齐与安全训练成果。该系列针对对抗性指令注入做了鲁棒性优化,降低被越权利用的风险。在隐私信息处理方面,模型被训练为对用户私密数据保持谨慎。Meta 表示这是实现其 personal superintelligence 目标所需的安全投入。
Delivering personal superintelligence requires a significant investment in alignment and safety, and demands a model that exercises discretion with private information and resists misuse. We trained the Muse Wonder family to lead on both dimensions, with robustness to adversarial instructions and careful handling of private information. 💬 1 🔄 3 ❤️ 40 👀 2765 📊 5 ⚡