the AI alignment problem is entirely a smokescreen designed to distract from the capital class alignment problem

@glyph

ML ethics: here's why including ZIP codes in the data used by a classifier is bad

AI ethics: what if some cryptogod hundreds of millennia in the future gets their feelings hurt by mean posts and decides to invent hell?

@glyph (I hate how little I had to exaggerate to make that joke.)
@xgranade I don't think there's an exaggeration here, just some uncharitable phrasing
@glyph @xgranade They would tend to say spacegod instead of god, intelligence instead of feelings, and spacehell instead of hell, because to them that makes it Science and Fact rather than religion or fantasy.