Ideally, this is where I would exhibit some example that demonstrates the utility of thinking this way: an ethical problem that utilitarianism can't answer well but a control theory approach can, or a self-help or educational problem that other methods couldn't resolve and this method can.
So I'm not entirely sure whether this is actually correct, and I could be entirely off, but could the control theory approach be relevant for problems like:
- If you have an unbounded utility function, it won't converge
- If you have a bounded utility function, you may consider a universe with (say) 10^18 tortured people to be equally bad as a universe with any higher number of tortured people
- Conversely, if you have a bounded utility function, you may consider a universe with (say) 10^18 units of positive utility to be equally good as a universe with any higher number of good things
- If you do have some clear specific goal (e.g. build a single paperclip factory), then after that goal has been fulfilled, you may keep building more paperclip factories just in case there was something wrong with the first factory, or your sense data is mistaken and you haven't actually built a factory, etc.
Intuitively it seems to me that the way that human goal-directed behavior works is by some mechanism bringing either desirable or undesirable things into our mental awareness, with the achievement or elimination of that thing then becoming the reference towards which feedback is applied. This kind of architecture might then help fix problems 2-3, in that if an AI becomes aware of there existing more bad things / there being the potential for more good things, it would begin to move towards fixing that, independent of how many other good things already existed. Problem 4 is trickier, but might be related to there some being set of criteria governing whether or not possibilities are brought into mental awareness.
Does this make sense?
Subscribe to RSS Feed
= f037147d6e6c911a85753b9abdedda8d)
Are you sure you are not attacking a strawman/nut picking? I mean, there are certainly people who believe that, but is it really a representative position among atheists (*)?
(* Here I assume we are talking about atheists who don't partecipate to a secular/political religion, as these ones lend towards fanaticism, therefore I suppose they are more likely to hold false and inflammatory beliefs as long as they support their ideology and demonize competing ideologies)
So why don't the Sun and the planets fall on the Earth?
In the Aristotelic model you still needed a distinction between terrestial mechanics, ruling the sublunary sphere where gravity but also friction, drag, decay, and all kinds of irreversible processes occur, and celestial mechanics, ruling the celestial spheres, where everything moves like clockwork rather than "falling down" without any apparent energy source and doesn't show any signs of decay and irreversibility that 17th century people could have observed with instruments of their time.
Before Newton unified terrestial and celestial mechanics, you needed to keep them separate whether you were using a geocentric or a heliocentric model. You still needed a sublunary sphere sphere around the Earth where things slow down and fall and break and decay on their way towards the End of Time, while God and the Angels watch us from their perfect and immutable Heaven.
Neither the geocentric nor the heliocentric model had an advantage in terms of explanatory power here.
If the earth has a sublunary sphere, that suggests the earth is 'special', which is certainly more parsimonious in a geocentric universe. Also why doesn't earth's sublunary sphere cause it to fall into the sun?