This comes up every couple of months like some freshly uncovered secret. You can see it in Google trends too. I'm surprised to see this being so prevalent over the fediverse, I thought karma farming wasn't a thing over here. 

My thoughts exactly. Also I wouldn't really like to risk my stuff by connecting to their infrastructure anyway. At least over here, I saw how incompetent they are. 

Yes, I just moved from github to a self hosted Forgejo instance the other week

Damn, I've been lied to 27 years ago! Thanks for sharing your experiences

Ooh, Australia, I have a question. Was PalTalk a big thing over there? Obviously way after what you described. I remember my father having an old classmate over from Australia and he introduced us to "The Internet", and how instant messaging was possible a cross borders through PalTalk. Even though I never heard anyone using it in Europe, even years past that encounter. 

From my other comment it looks like this dataset contains various strings that trigger refusal: https://huggingface.co/datasets/mlabonne/harmful_behaviors

Also, you might want to research this Heretic project, which aims to remove safeguards from local models as those might be similar to what's in the larger versions. Figuring out the phrases they test the safeguards with might have some decent results. 

Asking questions about Chinese politics and/or Tiananmen Square  stops most China based AI models, like Qwen and whatever is on Huawei phones. They aren't that high traffic yet, but are certainly in the list of "all ai models" 

In the videogame Wolfenstein: The New Order there's mentions from a character that might be loosely based on her, or at least the details are very similar. Look up "Ramona's diary" if you'd like to read more.