首页 > AI前沿 > Our approach to alignment research

Our approach to alignment research

OpenAI 2022-08-24 15:00 1 阅读 查看原文

Improving AI Alignment Through Human Feedback

We are improving our AI systems’ ability to learn from human feedback and to assist humans at evaluating AI.

Our goal is to build a sufficiently aligned AI system that can help us solve all other alignment problems.