Update: Arbital Scrape V2 I've scraped http://arbital.com as the site is unusably slow and hard to search for me. The scrape is locally browsable and plain HTML save for MathJax. https://drive.google.com/open?id=1b7dKhOzfMpFwngAeI8efeOzv147Lv_mx https://emma-borhanian.github.io/arbital-scrape/ If there's interest let me know as I may tidy up and open source my code. edit: working on this Mirror: www.obormot.net/arbital
Unbounded agentic selfishness isn't possible unless you can unboundedly index on and retrocausally compress "self". Otherwise future "you" is just this animal walking around, and how do you specify them in particular for good things to happen to? In practice, evil people do this by cancer like "make good things...
I want to gauge opinions. Do you think TDT/FDT imply magic is real? Do you think magic is real? Feel free to define magic, but I'd like to leave it at that simple pretheoretic pointer in order not to bias the results.
I found an interesting article by Eliezer on arbital: https://arbital.com/p/hyperexistential_separation/ > One seemingly obvious patch to avoid disutility maximization might be to give the AGI a utility function U=V+W where W says that the absolute worst possible thing that can happen is for a piece of paper to have written...
Some sites are free due to the coronavirus and we should scrape them. Please list any temporarily-free websites you know of, such as https://www.uptodate.com/ To download sites I recommend https://github.com/ArchiveTeam/grab-site Consider whether you want to use --no-offsite-links. Otherwise it will pull every linked page and its resources (and sometimes even...
I've scraped http://arbital.com as the site is unusably slow and hard to search for me. https://drive.google.com/open?id=1b7dKhOzfMpFwngAeI8efeOzv147Lv_mx https://mega.nz/#!SUQg1YxS!G7bmpNipcl1Ztugvr6l6sUJUu1D0gDg1-jA6oXLNEWg https://emma-borhanian.github.io/arbital-scrape/ The scrape is locally browsable and plain HTML save for MathJax and a few interactive demos. Source code included (with git history). (previously Arbital Scrape) Updates: Included source code, MathJax and link...
Update: Arbital Scrape V2 I've scraped http://arbital.com as the site is unusably slow and hard to search for me. The scrape is locally browsable and plain HTML save for MathJax. https://drive.google.com/open?id=1b7dKhOzfMpFwngAeI8efeOzv147Lv_mx https://emma-borhanian.github.io/arbital-scrape/ If there's interest let me know as I may tidy up and open source my code. edit: working...
Unbounded agentic selfishness isn't possible unless you can unboundedly index on and retrocausally compress "self". Otherwise future "you" is just this animal walking around, and how do you specify them in particular for good things to happen to? In practice, evil people do this by cancer like "make good things happen to people with my skin color".
If you believe humans are "not coherent agents" i.e. what values someone ends up with is underdetermined, then why would you believe that acquisition of ability to index on values as self is coacquired with the underdetermined acquisition of those values? Like, that would be inconsistently postulating both having and lacking "inner alignment".
(Note that Lesswrongers don't think about cybernetics much like "but how does the thing reference itself", if this style of argument seems unusual to you)
So what does "is magic real?", as a child might ask the question, correspond to?
I want to gauge opinions.
Do you think TDT/FDT imply magic is real? Do you think magic is real?
Feel free to define magic, but I'd like to leave it at that simple pretheoretic pointer in order not to bias the results.
Veganism?
Why does evil exist?
I found an interesting article by Eliezer on arbital: https://arbital.com/p/hyperexistential_separation/
One seemingly obvious patch to avoid disutility maximization might be to give the AGI a utility function U=V+W where W says that the absolute worst possible thing that can happen is for a piece of paper to have written on it the SHA256 hash of "Nopenopenope" plus 17
The article appears to be suggesting that in order to avoid an FAI accidentally(?) creating hell while trying to stop hell or think about hell, we could find some solution analogous to making the AI a positive utilitarian, so it would never even invent the idea of hell.
This appears to me to be making an ontological assumption that there's a zero-point between positive and negative value, which seems dubious but I'm confused.
Should AGIs think about hell sometimes? e.g. to stop it?
Some sites are free due to the coronavirus and we should scrape them. Please list any temporarily-free websites you know of, such as https://www.uptodate.com/
To download sites I recommend https://github.com/ArchiveTeam/grab-site
Consider whether you want to use --no-offsite-links. Otherwise it will pull every linked page and its resources (and sometimes even embedded videos).
Do these things feel logically impossible per se?
Yes, same qualia as looking at an Escher staircase IRL but feels more fundamental.
Do they feel impossible because they contradict other things that you believe are true?
No. I can't break down why they feel impossible.
Do you draw the conclusion that the impossible-seeming things genuinely cannot exist or (in the case of self-perception?) genuinely do not exist, despite appearances?
Kinda but I can't maintain that because milliseconds later I perceive the "impossible" qualia again.
Free will used to feel impossible but now that I understand free will as related to e.g. the 5-and-10 problem it's more... manipulable somehow.
standard model of PA = schelling model of PA?
5. A second machine, designed solely to neutralize an evil super-intelligent machine will win every time, if given similar amounts of computing resources (because specialized machines always beat general ones).
This implies you have some resource you didn't fully imbue to the first AI, that you still have available to imbue to the second. What is that resource?
I feel a sense of impossibility that "anything could exist at all".
I feel a sense of impossibility when I contemplate the recursive nature of perceiving myself perceiving thoughts.
I feel a sense of impossibility about something unspeakable that comes before and is outside anything else.
How are we sure we mean the same thing by the word consciousness though? All I can tell for sure is that ppl think consciousness is "impossible" (cus they try to invent quantum phlogiston to explain it), and something about consciousness engendering moral worth.
I don't think I'd have less moral worth if I couldn't recognize myself in a mirror. I still have moral worth when I'm not introspecting.
I get the sense of impossibility but I get it about lots of things, e.g. Greg Egan's dust from permutation city.
I feel like maybe I'm missing something other people are experiencing here, but maybe not.
spectrum of qualia of rapid muscle movement:
1. wiggle back and forth with no delay
2. effort required to make individual movements one in a row
some actions are only sometimes available to me in form #2 e.g. glossolalia, patterns of rapid eye movement
sometimes it seems like a matter of training e.g. learning to wiggle my ears
I've scraped http://arbital.com as the site is unusably slow and hard to search for me.
https://drive.google.com/open?id=1b7dKhOzfMpFwngAeI8efeOzv147Lv_mx
https://mega.nz/#!SUQg1YxS!G7bmpNipcl1Ztugvr6l6sUJUu1D0gDg1-jA6oXLNEWg
https://emma-borhanian.github.io/arbital-scrape/
The scrape is locally browsable and plain HTML save for MathJax and a few interactive demos. Source code included (with git history).
(previously Arbital Scrape)
Updates: Included source code, MathJax and link formatting, cross-linking, missing pages, etc
Source: https://github.com/emma-borhanian/arbital-scrape
Mirror: www.obormot.net/arbital
Update: Arbital Scrape V2
I've scraped http://arbital.com as the site is unusably slow and hard to search for me.
The scrape is locally browsable and plain HTML save for MathJax.
https://drive.google.com/open?id=1b7dKhOzfMpFwngAeI8efeOzv147Lv_mx
https://emma-borhanian.github.io/arbital-scrape/
If there's interest let me know as I may tidy up and open source my code. edit: working on this
Mirror: www.obormot.net/arbital
Without bound, as in, without there existing some specific bound you will never surpass.
Make yourself easier for your past self to index on. e.g. for an evil version, if Horde Prime wants Horde clones to work to benefit Horde Prime, Horde Prime can work to place himself in the center of the universe, which he previously programmed other Hordes to care about.
I'm saying something closest to #3. In order to specify an individual, you have to be able to point at them in some way.