Safety and alignment in an era of long-horizon models

摘要 · OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.

阅读原文 · OpenAI →

Safety and alignment in an era of long-horizon models

大模型

OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.

原文：https://openai.com/index/safety-alignment-long-horizon-models

0 条评论 · 观点来自社区

评论区 0 条讨论

以 … 的身份发言

还没有评论，来抢沙发。