Skip to main content
Artificial Intelligence

Improving Model Safety Behavior with Rule-Based Rewards

OpenAI Blog · · 4 views

We’ve developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely without extensive human data collection.

We’ve developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely without extensive human data collection.