I should say that I appreciate the value of getting models to censor content for certain use cases. You don't want your support bot sexting your users.That kind of alignment makes sense, and is…

Posters: xlr8harder. xlr8harder

2 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/xlr8harder/status/1782345419990925369