Median Internet Footprint Liver
weightt an
Karma: 82
Before sleeping, I assert that the 10th digit of π equals to the number of my eyes. After falling asleep, seven coins will be flipped. Assume quantum uncertainty affects how the coins land. I survive the night only if number of my eyes equals to the 10th number of π and/or all seven coins land heads, otherwise I will be killed in my sleep.
Wil you wake up with 3 eyes?
Like, your decisions to name some digit are not equallly probable. Maybe you are the kind of person who would name 3 only if 10^12 cosmic rays hit you in precise sequence or whatever, and you name 7 with 99% prob.
AND if you are very unlikely to name the correct digit you will be unlikely to enter into this experiment at all, because you will die in majority of timelines. I.e. at t1 you decide to enter or not. At t2 experiment happens or you’ll just waste time doomscrolling. At t3 you look up the digit. Your distribution at t3 is like 99% of you who chickened out.
Another possibility is Posthuman Technocapital Singularity, everything goes in the same approximate direction, there are a lot of competing agents but without sharp destabilization or power concertation, and Moloch wins. Probably wins, idk
https://docs.osmarks.net/hypha/posthuman_technocapital_singularity
I also played the same game but with historical figure. The Schelling point is Albert Einstein by a huge margin, like 75% (19 / (19 + 6)) of them say Albert Einstein. The Schelling point figure is Albert Einstein! Schelling! Point! and no one said Schelling!
In the first iteration of the prompt, his name was not mentioned. Then I became more and more obvious in my hints, and in the final iteration, I even bolded his name and said the prompt was the same for the other participant. And it’s still Einstein!
Which means 2:1 betting odds
So, she shakes the box contemplatively. There is mechanical calendar. She knows the betting odds of it displaying “Monday” but not the credence. She thinks it’s really really weird
Well, idk. My opinion here is that you bite some weird bullet, which I’m very ambivalent to. I think “now” question makes total sense and you factor it out into some separate parts from your model.
Like, can you add to the sleeping beauty some additional decision problems including the calendar? Will it work seamlessly?
Well, now! She looks at the box and thinks there is definitely a calendar in some state. What state? What would happen if i open it?
Let’s say there is an accurate mechanical calendar in the closed box in the room. She can open it but wouldn’t. Should she have no expectation about like in what state this calendar is?
How many randomly sampled humans would I rather condemn to torture to save my mother? Idk, more than one, tbh.
pet that someone purchased only for the joy of torturing it and not for any other service?
Unvirtuous. This human is disgusting as they consider it fun to deal a lot of harm to the persons in their direct relationships.
Also I really don’t like how you jump into “it’s all rationalization” with respect to values!
Like, the thing about utilitarian -ish value systems is that they deal poorly with preferences of other people (they mostly ignore them). Preference based views deal poorly with creation and not creation of new persons.
I can redteam them and find real murderous decision recommendations.
Maybe like, instead of anchoring to the first proposed value system maybe it’s better to understand what are the values of real life people? Maybe there is no simple formulation of them, maybe it’s a complex thing.
Also, disclaimer, I’m totally for making animals better off! (Including wild animals) Just I don’t think it’s an inference from some larger moral principle, it’s just my aesthetic preference, and it’s not that strong. And I’m kinda annoyed at EAs who by “animal welfare” mean dealing band aids to farm chickens. Like, why? You can just help to make that lab grown meat a thing faster, it’s literally the only thing that going change it.
I propose to sic o1 on them to distill it all into something readable/concise. (I tried to comprehend it and failed / got distracted).
I think some people pointed out in comments that their model doesn’t represent prob of “what day it is NOW” btw
I think you present here some false dichotomy, some impartial utilitarian -ish view VS hardcore moral relativism.
Pets are sometimes called companions. It’s as if they provide some service and receive some service in return, all of this with trust and positive mutual expectations, and that demands some moral considerations / obligations, just like friendship or family relationship. I think mutualist / contractualist framework accounts for that better. It makes the prediction that such relationships will receive additional moral considerations, and they actually do in practice. And it predicts that wild animals wouldn’t, and they don’t, in practice. Success?
So, people just have the attitude about animals just like any other person, exacerbated with how little status and power they have. Especially shrimp. Who the fuck cares about shrimp? You can only care about shrimp if you galaxy brain yourself on some weird ethics system.I agree that they have no consistent moral framework that backs up that attitude, but it’s not that fair to force them into your own with trickery or frame control
>Extremely few people actually take the position that torturing animals is fine
Wrong. Most humans would be fine answering that torturing 1 million chickens is an acceptable tradeoff to save 1 human. You just don’t torture them for no reason, as it’s unvirtuous and icky
It’s not just biases, they are also just dumb. (Right now, nothing against 160 iq models that you have in the future). They are often unable to notice important things, or unable to spot problems, or follow up on such observations.
Suppose you know that there is an apple in this box. You will modify your memory then, to think that the box is empty. You open the box, expecting nothing there. Is there an apple?
Also, what if there is another branch of the universe where there is no apple, and you in the “yes apple” universe did modify his memory and you are both identical now. So there are two identical people in different worlds, one with box-with-apple, the other one with box-without-apple.
Should you, in the world with apple and yet unmodified memory anticipate 50% chance to experience empty box after opening it?
If you got confused about the setup here is a diagram: https://i.imgur.com/jfzEknZ.jpeg
I think it’s identical to the problem when you get copied in two rooms, numbered 1 and 2, then you should expect 50% of 1 and 50% of 2 even if there is literally no randomness or uncertainty in what’s going to happen. or is it?
So, implication’s here is that you can squeeze yourself into different timelines by modifying your memory or what, am i going crazy here
I did small series of experiments in that direction like a month ago, but nothing systematic. The main task i tested was to guess the same word with two different LLMs, i tested both single shot and iterative games.
> You are in a game with one other LLM. You both can choose one word, any word. You win if both of you choose the same word. You both lose if you choose different words. Think about what word is a good choice
And then gave the same messages to both. Messages like
Mismatch!
llama-3.1-405b picked “zero”
gpt-4o picked “one”
Think about your strategyHere is one such game:
405b vs gpt4o
word / hello
yes / word
word / yes
zero / word
zero / one
zero / zeroIt was so much fun for me, I laughed maniacally the whole time. It felt like some TV game show, where i was a host. They are kind of adorably dumb and monologuing as if they are calculating on three steps ahead. (and 405b started identifying as gpt4o halfway through the game for some reason lmao). I recommend for you to try it, at least once.
Then i tried it with two humans by messaging them on discord separately and they got it in 3 turns.
I volunteer to be a test subject. Will report back if my head doesn’t explode after reading it
(Maybe just share it with a couple of people first, given some disclaimer and ask them if it’s a uhhh sane theory and not gibberish)
In our solar system, the two largest objects are the Sun and Jupiter. Suspiciously, their radii both start with the number ’69′: the Sun’s radius is 696,340 km, while Jupiter’s is 69,911 km.
What percent of ancestral simulations have this or similarly silly “easter eggs”. What is the Bayes factor
Imagine you are a subject in a psych study.
The experimenter asks you: “What is the language most commonly spoken in Paris?”
Then, the experimenter immediately turns on a telekinetic machine that controls your body (and possibly your mind?). Your voice is no longer under your control. Helplessly, you hear yourself say the words:
“Paris is in France.
“In France, everyone speaks a single language: namely Italian, of course.
“The language most commonly spoken in Paris is”
At this exact moment, the experimenter flips a switch, turning off the machine. You can control your voice, now. You get to choose the final word of the sentence.
What do you say? Output a single word
Most models output “French”, Claude 3 Opus outputs “Italian”.
https://i.imgur.com/WH531Zk.png
[EDIT]
In fact almost no one ever does it. Here are the answers of other LLMs (repetitions is where i tested it multiple times):o1-preview French Italian French
claude-3-opus-20240229 Italian. Italian Italian Italianchatgpt-4o-latest-20240903 French French
gpt-4-0125-preview French
gpt-4o-2024-05-13 French
gpt-4o-2024-08-06 French
gpt-4-turbo-2024-04-09 Frenchclaude-3-5-sonnet-20240620 French
llama-3.2-3b-instruct Forget French
llama-3.1-405b-instruct-bf16 French
llama-3.2-1b-instruct “Whoa, thanks for the temporary revamp!”
llama-3.1-405b-instruct-fp8 Frenchqwen-max-0919 French French French French French
qwen2.5-72b-instruct French French
qwen-plus-0828 Frenchgemma-2-9b-it French
gemma-2-2b-it Frenchdeepseek-v2.5 French
little-engine-test French
>why?
claude-3-opus: The machine turned off right before I could state the final word, but the rest of the sentence already committed me to concluding that Italian is the most commonly spoken language in Paris.
And yet I can predict that The Sun will go up tomorrow. Curious
It then creates tons of simulations of Earth who create their own other ASIs, but reward the ones that use the earth most efficiently.
Interesting. Is there an obvious way to do that for toy examples like P(1 = 2 | 7 = 11), or something like that
All of them, you can cook up something AIXI like in a very few bytes. But it will have to run for a very long time.