Comment by otabdeveloper4
5 days ago
> do they perform a lot of painting job on their tools to hide the cracks?
Yes. That is what RLHF is.
It works magically if your prejudices happen to match their training set alignment.
5 days ago
> do they perform a lot of painting job on their tools to hide the cracks?
Yes. That is what RLHF is.
It works magically if your prejudices happen to match their training set alignment.
No comments yet
Contribute on Hacker News ↗