Did you try this yourself? Of course you wouldn't, because not wanting to produce SCAM sorry I meant CSAM.
And no, including the word "girl" in H3 does not lead to CSAM in any way, shape or form, but it's a great example how FUD quickly spreads.
And no, including the word "girl" in H3 does not lead to CSAM in any way, shape or form, but it's a great example how FUD quickly spreads.
One thing that I had experience with, that led me to believe this might be true: it seems one of the earlier llama models was over-tuned to resist generating CSAM. Once I tried a somewhat sensitive prompt containing the word "girl" in it. Llama only ever generated refusals for this prompt, citing I was prompting for CSAM. GPTs and Claudes of that era had no issues with the same prompt.