As long as we can swear more, we’ll be ok.

X1 is bullshit to argue about, it’s about X2.

Since the models are so censored and “proper” in their grammar, you can pretty easily stand out

I've found swearing to be a pretty decent heuristic for whether I'm talking to an actual person or not. Either it'll remain a decent heuristic or we'll get some Malcolm Tucker-esque LLMs out of it!