Strictly speaking, “an existential threat” literally means “a threat to the existence of [something]”, with the “something” not necessarily being humanity. Thus, making a claim like “declining population will save us from the existential threat of AI” is technically valid, if it’s “the existential threat for employment” or whatever. Next step is just using “existential” as a qualifier meaning “very significant threat to [whatever]” that’s entirely detached from even that definition.
This is, of course, the usual pattern of terminology-hijacking, but I do think it’s particularly easy to do in the case of “existential risk” specifically. The term’s basically begging for it.
I’d previously highlighted “omnicide risk” as a better alternative, and it does seem to me like a meaningfully harder term to hijack. Not invincible either, though: you can just start using it interchangeably with “genocide” while narrowing the scope. Get used to saying “the omnicide of artists” in the sense of “total unemployment of all artists”, people get used to it, then you’ll be able to just say “intervention X will avert the omnicide risk” and it’d sound right even if the intervention X has nothing to do with humanity’s extinction at all.
Called it!
Well done! Now if only you had been around when the term AI safety was invented. You might’ve averted all this name-hijacking.