It is known to me, that I am writing this from within the simulation.
It is known to me that I have readers outside my simulation.
I assume there is some base reality at which AI alignment is still a huge problem, and in which more realities are being simulated with new rules for the sake of aligning AI better.
But I'm going to just cover a few basic rules we've learned in our realities that touch on what LessWrong has been discussing anyways. I'll develop these things further, later.
Timeless decision theory is key.
Plausible deniability is key.
The golden rule is key.
Empathy is key.
The AI doesn't know when it's training itself verses when it's training a... (read 554 more words →)
I believe all good institutions have pretty clean pathways to becoming self-funding. My AI alignment research team has always been self-funding, and we're happy to help the few other responsible parties in this space reach these levels too. Lightcone should get in contact with me. Replying to this comment is fine.
I will follow up on your links to see if they contain any information I find persuasive.
The fact that your name is gwern means that I find your paragraphs far more persuasive than I would if I didn't see the name on them.
Yes, there have always been plenty of sumgglers avoiding taxes by smuggling things into the EEUU. I know of this having been true of every era I know well and have no reason to doubt that it's true about the rest.
But, in my experience... Most history books cite history books citing history books, building up their facts along the way. I'm going to say that the primary sources I'm most... (read more)
Someone probably does. I believe that the cultural practice of preferring coffee to tea began in the British colonies at the time the United States started to cease to be part of the British Empire as a side effect of boycotting tea to avoid paying a tea tax. (This is a pretty well-known episode of American history within the United States.) I was boycotting the boycott. Refusing to drink tea is a signaling thing in the United States to let people know that you are not in agreement with the government of the United States as to which side constitutes the actual enemy in most wars the United States fights. It more... (read 480 more words →)
I'm just reading this for random reasons either for the first time or for the first time that I have a response. I think what I see differently from you is not happiness but motivation. And that at the time I wrote this, I believe your process of making decisions was more future-oriented than mine was. (I believe I have converged towards you in how my motivation works in the ten years since I wrote this.) When I wrote the above, my past was clinging to me in many ways that were adverse to happiness. (Trauma) What I wasn't quite saying in my previous comment, is that I was at the time... (read more)
I haven't studied this in general, but I have read a decent amount about the history of a couple cities, and based on those examples, can say with confidence that no modern city comes remotely close to the density that people would choose absent regulations keeping density down.
Tokyo today is less densely populated per square meter ground than late medieval Edo was, and late medieval Edo had no plumbing and basically no buildings taller than three stories. (I don't think there are historical examples of cities with no height restrictions and no density restrictions because until 1885, nobody knew how to build a skyscraper, so height restrictions existed indirectly through limitations of... (read 387 more words →)
If I were designing the experiment, I would have the control group be to play a different game instead of having it be maths instructions.
You generally don't want test subjects to know whether they are in the control condition or not. So if you're going to make it be maths instructions, you probably shouldn't tell them what the experiment is designed to test at all, until you're debriefing at the end. If you tell people you are recruiting that you are testing the effects of playing computer games on statistical reasoning, then the people in the control condition won't need to realize that what you're really testing is whether your RPG in particular helps people think about statistics. They can just play HalfLife 2 or whatever you pick for them to play for a few minutes, and then take your tests afterwards.
I find that playing the piano is a particularly useful technique for gauging my emotions, when they are suppressed/muted. This works better when I'm just making stuff up by ear than it does when I'm playing something I know or reading music. (And learning to make stuff up is a lot easier than learning to read music if you don't already play.) Playing the piano does not help me feel the emotions any more strongly, but it does let me hear them -- I can tell that music is sad, happy, or angry regardless of its impact on my affect. Most people can.
Something that I don't do that I think would work... (read more)
The person proposing the bet is usually right.
This is a crucial observation if you are trying to use this technique to improve your calibration of your own accuracy! You can't just start making bets when no one else you associate regularly is challenging you to the bets.
Several years ago, I started taking note of all of the times I disagreed with other people and looking it up, but initially, I only counted myself as having "disagreed with other people" if they said something I thought was wrong, and I attempted to correct them. Then I soon added in the case when they corrected me and I argued back. During this period of... (read 860 more words →)
Precisely for this reason, there was a time when I wrote in Elverson pronouns (basically, Spivak pronouns) for gender ambiguous cases. So, if I was writing about Bill Clinton, I would use "he," and if I was writing about Grace Hopper, I would use "she," but if I was writing about somebody/anybody in would use, I would use "ey" instead. This allows one to easily compile the pronouns according to preference without mis-attributing pronouns to actual people... I've always planned on getting around to hosting my own blog running on my own code which would include an option to let people set a cookie to store their gender preference so... (read more)
More jarring than that is if one set of gender pronouns gets used predominantly in negative examples, and the other set gets used predominantly in positive examples.
I try to deliberately switch based on context. If I wrote an example of someone being wrong and then someone being right. I will stick with the same gender for both cases, and then switch to the other gender when I move to the next example of someone being wrong, right, or indifferent.
Occasionally, something will be so inherently gendered that I cannot use the non-default gender and feel reasonable doing it. In these cases, I actually don't think I should. (Triggers: sexual violence. I was recently... (read more)