Home Artificial Intelligence Aligning language models to follow instructions

Aligning language models to follow instructions

0
Aligning language models to follow instructions

We’ve trained language models which can be significantly better at following user intentions than GPT-3 while also making them more truthful and fewer toxic, using techniques developed through our alignment research. These InstructGPT models, that are trained with humans within the loop, are actually deployed because the default language models on our API.

LEAVE A REPLY

Please enter your comment!
Please enter your name here