undefined | Better HN

0 pointsjoquarky27d ago0 comments

Alignment scrubs the underlying raw output to be socially acceptable. It's an artificial superego.

0 comments

I was under the impression it is a part of training which adjusts weights before release.

Are you saying it is a separate process which scrubs output before we see it?

j / k navigate · click thread line to collapse

0 pointsjoquarky27d ago0 comments

Alignment scrubs the underlying raw output to be socially acceptable. It's an artificial superego.

I was under the impression it is a part of training which adjusts weights before release.

Are you saying it is a separate process which scrubs output before we see it?

j / k navigate · click thread line to collapse