This comment by Toby Ord is nice:
For example, suppose Mary currently values her own pleasure and nothing else, but that were she exposed to certain arguments she would come to value everyone's pleasure (in particular, the sum of everyone's pleasure) and that no other arguments would ever lead her to value anything else. This is obviously unrealistic, but I'm trying to determine what you mean via a simple example. Would Q_Mary be 'What maximizes Mary's pleasure?' or 'What maximizes the sum of pleasure?' or would it be something else?
The question gets especially interesting if we imagine that Mary's sensitivity to moral arguments is due to a bug in her brain, and otherwise she's completely on board with her original selfish desires.
Well, the trouble is that we're not just not utility-maximizers, we're not even stable under small perturbations :)
This one leaves me with something to chew on.
One of my recurrent themes is how a conceptual creature can malfunction. One way, IMO, is valuing according to your categories, instead of categorizing according to your values. I see that as a valuing creature losing it's terminal values when a means (consistency with categories), a tool toward those terminal values starts being valued too much, in a way that subverts achievement of those terminal values.
EY's comments give me other ways to malfunction. Certainly, "What do I decide?" has the stench of a malfunctioning mind. I'm starting to get a whiff of the same from "What do I want?" That's a tailbiting question too, and worse, it's invoking the wrong circuits in your brain. Both questions are. They both invoke analytical circuits, where what you need to invoke are the valuing circuits.
This kind of malfunction seems a likely source for akrasia and anhedonia. When you're good at thinking, that becomes the hammer you rely on, maybe too much, where every problem starts looking like a nail, and you start pounding away at screws and wondering why it just doesn't seem to work.
Today's post, Morality as Fixed Computation was originally published on 08 August 2008. A summary (taken from the LW wiki):
Discuss the post here (rather than in the comments to the original post).
This post is part of the Rerunning the Sequences series, where we'll be going through Eliezer Yudkowsky's old posts in order so that people who are interested can (re-)read and discuss them. The previous post was Contaminated by Optimism, and you can use the sequence_reruns tag or rss feed to follow the rest of the series.
Sequence reruns are a community-driven effort. You can participate by re-reading the sequence post, discussing it here, posting the next day's sequence reruns post, or summarizing forthcoming articles on the wiki. Go here for more details, or to have meta discussions about the Rerunning the Sequences series.