Research

Our approach to alignment research

Source: OpenAI News 24 Aug 2022

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

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.

Why It Matters

Pendekatan ini penting kerana sistem yang lebih selaras dapat mengurangkan risiko tingkah laku tidak diingini dan memudahkan pengurusan keselamatan AI.

Keep Reading on NadiAI

Selected Related Articles