On: Heretic: Automatic censorship removal for language models

[int_19h]

A censored LLM might refuse to summarize text because it deems it offensive.

[blackqueeriroh → int_19h]

An LLM cannot “deem” anything.

[int_19h → blackqueeriroh]

I'm not interested in sophistry. You know perfectly well what I mean, and so does everyone else.