Safety and alignment in an era of long-horizon models

公司动态 OpenAI 原文语言:英文

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

原文摘录

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

以下是来源提供的简短摘录,完整内容请查看原文。

参考来源

← 返回每日简报