AI models rank their own safety in OpenAI’s new alignment research: Rules-based Rewards, a method from OpenAI that automates safety scoring, lets developers create clear-cut safety instructions for AI model fine-tuning. https://t.co/tj831nc7G0 #AI #Business

Lilian Weng@lilianweng

2 years ago

Rule-based rewards (RBRs) use model to provide RL signals based on a set of safety rubrics, making it easier to adapt to changing safety policies wo/ heavy dependency on human data. It also enables us to look at safety and capability in a more unified lens as a more capable… https://t.co/CdL6ee5cRO

Shaun Ralston@shaunralston

2 years ago

Rule-based rewards will make #AI more reliable without all that messy human data 😇 https://t.co/91QMyNXN7I