I like the intention and spirit of this.
Abstract: We construct a fully technical ethical goal function for AI by directly tackling the philosophical problems of metaethics and mental content. To simplify our reduction of these philosophical challenges into “merely” engineering ones, we suppose that unlimited computation and a complete low-level causal model of the world and the adult human brains in it are available.
I think that, just like with AIXI, these sorts of assumptions mean this approach is practically unworkable, it’s possible that like AIXI it can serve as a model of the ideal. I realize you have posted your code interspersed with comments, and I look forward to seeing more about this in the future as you develop your explanation of it (right now I lack a specific enough model of it to evaluate it beyond liking the intent).
I now have a much more readable explanation of my code. I’d be interested to hear your thoughts on it.