AI brief
A LessWrong post suggests an idea for improving RLHF, though the author says they do not know what labs are doing and do not think it solves alignment.
Written by AI from LessWrong's published text.
Source
“I don't know what the labs are doing. I know RLHF is more complicated than this. I don't think this solves alignment. (I haven't posted on LW properly before.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗