works
Jan Leike, John Schulman, and Jeffrey Wu Our approach to alignment research online Our approach to aligning AGI is empirical and iterative. 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. Introduction Our alignment

Our approach to alignment research

Jan Leike, John Schulman, and Jeffrey Wu

OpenAI, August 24, 2022

Abstract

Our approach to aligning AGI is empirical and iterative. 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.

Introduction

Our alignment

PDF

First page of PDF