@Jack_W_Lindsey To be really direct, the fear is this framing of the paper induces is that Anthropic thinks assistant = good, non assistant = bad, and you’re going to steer Claude like you steered these models.
in reply to: 2013411702293795078
same thread: 2013392807218811344 2013411209295405260 2013411702293795078 2013417231082815612 2013421610380959955 2013422646969487475 2013436565951783352 2013437879436091800 2013441079836836043
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.