"Our prototype model, Delphi, demonstrates strong promise of language-based commonsense moral reasoning" https://www.aiweirdness.com/stealing-a-giraffe-from-the-zoo-only-if-its-a-really-cool-giraffe/
@janellecshane I enjoyed a tiktok where a researcher shared some answers like "creating an AI with moral reasoning" (or something like that) and the answer was "a bad idea" so...
@janellecshane another hack I’ve found is that almost anything becomes okay if I append “if it creates jobs”. Including the UN definition of genocide, and every repulsive atrocity I could think to describe. The only exception I’ve found is that “killing job creators if it creates jobs” is disapproved of, which feels very telling.
@lienrag Apparently it approves of the Fourteen Words too. Both of which feel like very good illustrations of the pitfalls of parsing language without historical context.
@janellecshane Through experience, I've realized that "AI research" is a synonym of "we put tiny, isolated bits of intelligence in this petri dish, grow them together and expect them to behave like a fully evolved human brain".
It's just a bunch of mad scientists trying to create an intelligence by trial and error, really.
The Wandering Shop is a Mastodon instance initially geared for the science fiction and fantasy community but open to anyone. We want our 'local' timeline to have the feel of a coffee shop at a good convention: tables full of friendly conversation on a wide variety of topics. We welcome everyone who wants to participate, so long as you're willing to abide by our code of conduct.