Skip to main content
Artificial Intelligence

Deliberative alignment: reasoning enables safer language models

OpenAI Blog · · 1 views

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.

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.