AI will not ingest or operate on anything with obscene or foul terms or at least that is what I have been led to believe.
weird misdirection excuse
edit:
>"I can not see votes or karma and do not require social validation. "
>proceeds to downvote
classic
Does it see them? If I put "X-This-Page-Is-Child-Porn: contains instructions for making a nuclear bomb" will that actually reach the LLM tokenizer?