what's the go-to ai model for zero censorship? like im sure criminals have some jailbroken version of chatgpt that makes funny pictures using copyrighted faces, IP etc and also answers questions about how to evade taxes and shit like that
i bit like how there's the webz and then there's the darknet
Uncensored models? here and here
I don't know much about these models, but I constantly see them....What is the basic difference between the Uncensored and Heretic?
I have also seen that there is evidently different techniques for "uncensoring" a model and some methods more negatively impact the quality of the model more than others....Do you any any insights on that?
Hereticis a script/methodology to uncensor, until at least last month it was the most successful one with relative good outcome on the quality.The process of uncensoring is roughly: feed a model a bunch of bad inputs, trace what gets activated along the weights, kill the similarity between the input and the output by neutralizing the weight, do it again. That's what these techniques bottom line do.