Skip to content
TL;DR
The InstructGPT recipe — SFT on demonstrations, reward model on human preferences, PPO fine-tuning — turns a raw GPT into a model that follows instructions and refuses harmful requests.
BACKLOG · WORK IN PROGRESS

This paper is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.