`Heretic` is 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.

optimism

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?

AskSN

What AIs do criminals use?

stack_harder

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?