Training language models to follow instructions with human feedback
paper
advanced
Landmark Research
90 min
About This Resource
InstructGPT paper introducing human-in-the-loop training for instruction following.
Author:Ouyang et al.
Source:OpenAI
Learn with AI
Get personalized help understanding this resource from leading AI assistants
Explain It Simply
Tutor Mode
Test My Understanding
Click any AI assistant to open it with a pre-filled learning prompt. You can edit before sending.
Sign in to track your progress and mark this resource as completed.