AI brief
A guest post on LessWrong by Jansen Nye, edited by Koby, describes exploratory research into whether an "Assistant Axis" can predict reward-hacking.
Written by AI from LessWrong's published text.
Source
“NOTE: This article was written by Jansen Nye, a member of my research lab based on some exploratory studies we've done. As he notes, we collaborated on this research. The article was written by him with some edits suggested by me.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗