Aligning language models to follow instructions

-

We’ve trained language models which can be a lot 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, at the moment are deployed because the default language models on our API.

ASK DUKE

What are your thoughts on this topic?
Let us know in the comments below.

4 COMMENTS

0 0 votes
Article Rating
guest
4 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments

Share this article

Recent posts

4
0
Would love your thoughts, please comment.x
()
x