@roy_calum @Cal @munin Yeah, the crazy thing about content warning is that if you describe why you’re planting it then the filter itself that people use seems to be doing the job better. I don’t know it’s one of those corner cases that filtering words makes a whole lot more sense.

@munin I mean, what do they expect. LLMs make the computers themselves open to social engineering. I've seen over and over that social engineering on people will work, no matter the training, under the right situations. I don't expect LLMs to ever be any different.