This is kinda like that thing about how psychic mediums supposedly can't medium if there's a skeptic in the room. Goes to show that AI really is a modern-day ouija board.

▲

ctrust 2 hours ago | parent [-]

The accurate inferences that can be drawn from subtle linguistic attributes should freak you out more than they do.

	▲	alchemism 37 minutes ago \| parent [-]
		Switching one good synonym can send the model off an entirely different direction in response, or so I’ve observed.