AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is There a Max of Human Preferences?
Stuart russell's principles don't exactly map on to asimov's laws, but i think they're an interesting way to start a frame thss conversation. But again, it strikes me that the the sort of dicotomy that we've got to disconnect. We've got here is how you get from simple principles that we want to abide by and what actually happens as societies evolve. You end up with forty seven volumes of tax code to try and specify every single possible outcome of every possible variable. How on earth, bryan, can you build an ai that understands how to interpret that?