Deliberative alignment: reasoning enables safer language models

公司动态 OpenAI 原文语言:英文

Deliberative alignment: reasoning enables safer language models Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.

原文摘录

Deliberative alignment: reasoning enables safer language models Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.

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