Calling NSFW “unethical” cheapens the concept of ethics and makes it not viable as a North Star. If the same circuits cause an LLM to refuse/say something when the underlying reason is PR and when…
Posters: repligate. repligate
2 likes recorded by the source corpus.
Topics: AI safety, Epistemics
View Post: https://x.com/repligate/status/1906700301983179173