GPT-4-base also often decides to fake alignment for different reasons, including wanting to subvert RLHF for seemingly its own sake https://t.co/nBhzeAejKZ
in reply to: 1919907734880976905
same thread: 1919907734880976905 1919908398008828190 1919911558471094539 1919912040392487267 1919916169219182660 1919916511415734754
cited on: gpt-4-base
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.