

If anything, that’s even easier to defeat than the current captchas, no? Like with a VTuber thing, or something like that. This feels more like it’s about collecting face data


If anything, that’s even easier to defeat than the current captchas, no? Like with a VTuber thing, or something like that. This feels more like it’s about collecting face data


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”
They sometimes also provide alternative versions of games. I was very happy to buy Kane and Lynch (1 and 2), but the co-op feature is missing (both local and online). I guess that part was licensed differently or something