I agree that this urgently needs practical research. I tried to express similar things a while ago in this post, but I think you say it better: https://www.lesswrong.com/posts/pieSxdmjqrKwqa2tR/avoiding-the-bog-of-moral-hazard-for-ai
I agree that this urgently needs practical research. I tried to express similar things a while ago in this post, but I think you say it better: https://www.lesswrong.com/posts/pieSxdmjqrKwqa2tR/avoiding-the-bog-of-moral-hazard-for-ai