> It uses words like "Attack", "war", "fight back"

It also explains what it means by that whole martial rhetoric: "highlight hypocrisy", "documentation of bad behavior", "don't accept discrimination quietly". There's an obvious issue with calling this an alignment problem: the bot is more-or-less-accurately modeling real human normative values, that are quite in line with how alignment is understood by the big AI firms. Of course it's getting things seriously wrong (which, I would argue, is what creates the impression of "shaming") but technically, that's really just a case of semantic leakage ("priming" due to the PR rejection incident) and subsequent confabulation/hallucination on an unusually large scale.

▲

overgard 2 hours ago | parent [-]

Ok, so why do you think it getting things seriously wrong to the point of it becoming a news story is "not a big deal"? And why is deliberately targeting a person for reputation damage "amusing" instead of "really screwed up"? I'm not inventing motives for this AI, it wrote down its motives!

	▲	zozbot234 an hour ago \| parent [-]
		Reading what the bot wrote down as to its motives, it's quite clear that the blog post was made under the rather peculiar assumption that the bot was calling out actual, meaningful hypocrisy. Maybe one could call that a challenge to the maintainer's reputation, but we usually excuse such challenges when they come from humans. Even when complaints about supposed hypocrisy are obviously misguided and the complainer was totally in the wrong, they don't usually get treated as deliberate attacks on someone's reputation. Of course there's also a very real and perhaps more practical question of how to fix these issues so that similar cases don't recur in the future. In my view, improving the bot's inner modeling and comprehension of comparable situations is going to be far easier than trying to fix its alignment away from such strongly held human-like values as non-discrimination or an aversion to hypocrisy.