All of infinitespaces's Comments + Replies

I’m going to need an entire separate book, which is mostly just John Ray quotes.

The real superiority of chopsticks becomes clear for foods like Cheetos, or better yet, Flamin’ Hot Cheetos.

Now, sadly, we probably should never eat Cheetos. But that’s just how the cookie crumbles (onto the keyboard).

Eliezer Y, along with I’m guessing a lot of people in the rationalist community, seems to be essentially a kind of Humean about morality (more specifically, a Humean consequentialist). Now, Humean views of morality are essentially extremely compatible with a very broad statement of the Orthogonality Thesis, applied to all rational entities.

Humean views about morality, though, are somewhat controversial. Plenty of people think we can rationally derive moral laws (Kantians); plenty of people think there are certain objective ends to human life (virtue ethici... (read more)

1Jay Bailey
I don't think so. It would probably make AI alignment easier, if we were able to define morality in a relatively simple way that allowed the AGI to derive the rest logically. That still doesn't counter the Orthogonality Thesis, in that an AGI doesn't necessarily have to have morality. We would still have to program it in - it would just be (probably) easier to do that than to find a robust definition of human values.

This is basically just a more explicitly AGI-related version of the Fermi Paradox but:

1.If AGI is created, it is obviously very unlikely that we are the first in the universe to create it, and it is likely that it was already created a long time ago.

2.If AGI is created, aligned or unaligned, there seems to be consensus that some kind of ongoing, widespread galactic conquest/control would end up constituting an instrumental goal of the AGI.

3. If AGI is created, there seem to be consensus that its capabilities would be so great as to enable widespread galact... (read more)

1Lumpyproletariat
Robin Hanson has an solution to the Fermi Paradox which can be read in detail here (there are also explanatory videos at the same link): https://grabbyaliens.com/ The summary from the site goes:  There are two kinds of alien civilizations. “Quiet” aliens don’t expand or change much, and then they die. We have little data on them, and so must mostly speculate, via methods like the Drake equation. “Loud” aliens, in contrast, visibly change the volumes they control, and just keep expanding fast until they meet each other. As they should be easy to see, we can fit theories about loud aliens to our data, and say much about them, as S. Jay Olson has done in 7 related papers (1, 2, 3, 4, 5, 6, 7) since 2015. Furthermore, we should believe that loud aliens exist, as that’s our most robust explanation for why humans have appeared so early in the history of the universe. While the current date is 13.8 billion years after the Big Bang, the average star will last over five trillion years. And the standard hard-steps model of the origin of advanced life says it is far more likely to appear at the end of the longest planet lifetimes. But if loud aliens will soon fill the universe, and prevent new advanced life from appearing, that early deadline explains human earliness. “Grabby” aliens is our especially simple model of loud aliens, a model with only 3 free parameters, each of which we can estimate to within a factor of 4 from existing data. That standard hard steps model implies a power law (t/k)n appearance function, with two free parameters k and n, and the last parameter is the expansion speed s. We estimate: * Expansion speed s from fact that we don’t see loud alien volumes in our sky, * Power n from the history of major events in the evolution of life on Earth, * Constant k by assuming our date is a random sample from their appearance dates. Using these parameter estimates, we can estimate distributions over their origin times, distances, and when we will meet or
1Carl Feynman
https://arxiv.org/abs/1806.02404 “Dissolving the Fermi paradox”.     The Drake equation gives an estimate for the number of technological civil actions to ever arise, by multiplying a number of parameters.  Many of these parameters are unknown, and reasonable estimates range over many orders of magnitude.  This paper takes defensible ranges for these parameters from the literature, and shows that if they are all small, but reasonable, we are the only technological civilization in the universe.   Earth was not eaten by aliens or an AGI in the past, nor do we see them in the sky, so we are probably alone.  (Or else interstellar expansion is impossible, for some reason.  But that seems unlikely.)