I keep bumping into a pattern in EA spaces: people are very comfortable being ambitious about epistemology and cause prioritisation, but surprisingly pessimistic or dismissive about moral realism, or seem attracted to moral anti-realism. Moral realism often gets caricatured as spooky – as if it posits a weird substance floating outside the universe, or some…
AI doesn’t need a moustache-twirling villain to go wrong – it just needs the wrong metaethics in an unforgiving game. In this post I argue that: (1) many human moral norms are shaped by competitive, “Molochian” pressures; (2) if we give AI a purely constructivist / anti-realist metaethic, it will inherit and amplify those pressures;…
Part 1 in an interview with Eric Sampson on Moral Realism. Note AI is referenced, but the bulk of the questions about AI are covered in part 2. Chapters 0:00 Intro 3:03 Why is moral realism attractive to AI Safety Research? 2:02 Background, & Personal reason to choose moral realism 4:00 Describing moral realism –…
Something I find attractive about moral realism, is that because ethical propositions (propositions contained in ethical sentences) refer to facts about actual reality (physical and/or logical), these facts should then be amenable to testing. This means that the landscape on which to judge moral aptness gets clearer and clearer the more we understand the…