微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开，或复制链接。
OpenAI Adds Controls That Should've Been There Already
RSS 官方收录 · 可信分层展示
关键摘要
OpenAI新增安全控制，回应上月Hugging Face事件
- 新控件针对前沿模型失控风险
- 源于上月Hugging Face安全事件
- 部分功能本应在模型发布前就已部署
AI 摘要 · 来源可核验
正文提要
The new AI security controls follow the Hugging Face incident last month, though many of these additions perhaps should have been in place prior to the frontier models escaping.
来源：https://www.darkreading.com/application-security/openai-adds-controls-already