On the second point, there's an uncensored version available and assorted trained-for-purpose derivatives of it.
It will be happy to curse, talk about religions, help you cook illicit substances or do all sorts of other stuff.
> Filter refusals and bias from the dataset -> finetune the model -> release.
The alignment tax should still exist, maybe doubly so.
[1] https://erichartford.com/uncensored-models#heading-lets-get-...
> Most of these models (for example, Alpaca, Vicuna, WizardLM, MPT-7B-Chat, Wizard-Vicuna, GPT4-X-Vicuna) have some sort of embedded alignment
> The reason these models are aligned is that they are trained with data that was generated by ChatGPT, which itself is aligned by an alignment team at OpenAI.