A lot of AI safety money in the West comes from tech billionaire donations. What kinds of things do rich people in China like donating to?
mxbutterfree
Karma: 88
Extinction does not feel as bad as it should
Mark Lippman’s writing
There was this twitter thread which seems very related. Someone bought a clicker counter to train themselves to notice joy and used this to reach the jhanas, and Mark Lippman replied with a warning against this kind of clicker practice, for causing “sharp, tangled karma”.I practice Zen.
Any recommendations for starting Zen (e.g. books, retreat recordings)? Is this one of the practices where having a teacher is essential?
This is interesting! .
my understanding of jhana is that it’s something that should arise naturally without even trying.
I’m curious if there’s a particular school of Buddhism or text(s) that informed your understanding of jhana? I would be curious to learn different takes on it, especially those that are more established.
intentionally creating meditation debt so that people can experience jhana via goodharting on the idea of the feeling of joy
Could you elaborate on what “meditation debt” means here?
you couldn’t trick yourself into mixing up joy for the idea of joy.
This is a somewhat reassuring idea, that maybe I am resistant to self-deception.
I’m glad that in the end you ended up feeling happier!
Thank you.
This is very interesting. Some questions I have are:
Is the mindscape something that you need to intentionally create and visualize in your head, or does it appear effortlessly?
Does the place look the same every time you use it?
Can you store things reliably in the mindscape, like a memory palace?
For me, retrieving memories often just looks like a black screen for several seconds before the memory appears. I can tell my mind to create some kind of visualization while it does this and it does create something (like rifling through a bunch of folders), but it’s unclear to me if this is helping or not.
Jhana 0
It’s simply less costly for elected officials to go against donors on low-public salience issues
This sentence isn’t parsing for me, should it be “to go against voters”?
So an explanation has to exist! What is it? I claim there are really only two answers [consequentialism and imitative learning] that work in practice.
How do we know that these are the only two answers?
I would be interested in the list of your favourite links!
Given an aligned AGI, to what extent are people ok with letting the AGI modify us? Examples of such modifications include (feel free to add to the list):
Curing aging/illnesses
Significantly altering our biological form
Converting us to digital life forms
Reducing/Removing the capacity to suffer
Giving everyone instant jhanas/stream entry/etc.
Altering our desires to make them easier to satisfy
Increasing our intelligence (although this might be an alignment risk?)
Decreasing our intelligence
Refactoring our brains entirely
What exact parts of being “human” do we want to preserve?
A “moonshot idea” I saw brought up is getting Yudkowsky’s Harry Potter fanfiction translated into Chinese (please never ever do this).
This has already been done, and has pretty good reviews and some discussions.
I’ve looked through the EA/Rationalist/AI Safety forums in China
If these are public, could you post the links to them?
there is only one group doing technical alignment work in China
Do you know the name of the group, and what kinds of approaches they are taking toward technical alignment?
I’ll use this comment to collect things I find.
Are there any alignment approaches that try to replicate how children end up loving their parents (or vice versa), except with AI and humans? Alternatively, approaches that look like getting an AI to do Buddhist lovingkindness?
For derendering latex in Emacs, see https://github.com/io12/org-fragtog.
For drawing images in line, you could try https://github.com/misohena/el-easydraw.
I like this idea and think it is worth exploring. It is not even just with training new models; AGI have to worry about misalignment with every self-modification and every interaction with the environment that changes itself.
Perhaps there are even ways to deter an AGI from self-improvement, by making misalignment more likely.
Some caveats are:
AGI may not take alignment seriously. We already have plenty of examples of general intelligences who don’t.
AGI can still increase its capabilities without training new models, e.g. by getting more compute
If an AGI decides to solve alignment before significant self-improvement, it will very likely be overtaken by other humans or AGI who don’t care as much about alignment.
Sufficiently many Godzillas as an alignment strategy
Escape. Invest in space travel and escape the solar system before they arrive.
If your AI timelines are long, this may be a viable strategy for preserving the human species in the event of unaligned AGI.
In your AI timelines are short, a budget solution is to just send human brains into space and hope they will be found and revived by other powerful species (hopefully at least one of them is “benevolent”).
See also Silence by alkjash.