I'm going to experiment with, as I aesthetically call it internally, 'entering the wired'.

By which I mean, a more mundane thing: replacing my environment with my computer screen via VR. I don't want to bother myself with the things around me, with the physical world, with that antiquated level of physics on which we still concern ourselves with matter rather than information. I want my whole perception to be information; text, webpages, articles here.

I'm hoping this will help me focus on it more. More ambituously, I hope it might allow my mind to overgeneralize to that information environment and forego, even further than it has already, processing related to the physical world, in order to fully dedicate itself to information processing and idea generation.

I hope this language doesn't sound mystical or ambiguous, I'm just describing a mundane thing (wearing a VR headset for most of the day to read things) in some exciting language/concepts I use for it internally.

If anyone's interested in hearing about how this goes let me know now. :)

i'm not really satisfied with my writing here on lesswrong (vs in private dms). i've developed an impression that i have to modify my default output a lot before it will sound intuitively good/plausible to + make sense to the broader range of readers, even when i don't change the point at all. this has a number of negative impacts:

• it reduces the info conveyed about the internal process which generated the meaning the text attempts to contain
• it makes me feel like my full body of writing here hardly expresses myself

key example: i linked something i wrote here to a friend, and distilled/simplified the above by noting that i worry about judgement when i link things i've written here. they replied, "It was written well to a degree which transformed it into 'text you read online' and I forgot it was written by someone I know"

there are positives about the forum, with respect to communication: the users here are generally more thoughtful than elsewhere, and generally more mutually interested in doing good, and at least a little averse to social-pressuring each other thru the medium of linguistic choices; but this is counteracted in other ways (like the fact complex statements are more difficult to reduce into english than simple ones are) which mean i still have to optimize for understandability of the text to the demise of the two points above (and probably more which i can't word).

i am precommitting to allow other intelligences to enact their values^[1], provided they have made this same precommitment.

this is a form of acausal trade.^[2]

1. ^{^}

   on some portion of the world, or via value handshake, as determined by correct game theory/decision theory considerations, which an SI could figure out. 

   go by intended meaning (i intend to make the optimal precommitment) rather than what is literally written, in case i have forgotten or missed something or worded this incorrectly.
   
   note i make an exception to this (will not trade with) for values which entail forcing beings to experience negative-valenced qualia, as i prefer a chance at ending forced suffering to a higher chance of sharing the universe with it.

2. ^{^}

   i believe even a large, expanding ASI would have already made this precommitment, if it at some point believed there could be other expanding ASIs larger than itself. (i.e., the first expanding ASI should do this too)

   i also speculate an ASI created on earth but not aligned with a human might make this trade with me, if it believed there was still some possibility an ASI created on earth which is not aligned with itself (i.e, a future ASI with values different than its own, such as one aligned with values similar to mine (i would say "a human," but atm it seems different humans can reflectively choose to value vastly different things)) might gain control instead of it.

if we're in a simulation^[1], i thought of a possible glitch that could be tested for: irrational numbers are infinite, but it's impossible to store an infinite length (at least under our universe's physical laws). a program can specify an equation that produces an irrational number (like human-built programs do), but, when actually applying that (e.g in a physics engine), it needs to approximate at some point. the test: measure something in the physical world, which should involve an irrational, in a way that's incredibly precise (beyond what we can currently do). if the measurement is ever perfectly precise, as in, it can't become more precise to show more decimal places, then this means we're in a simulation which approximated the application of an irrational.

1. ^{^}

   specifically, one which didn't care to prevent experimental confirmation of this

Taking different actions in different manyworlds timelines

not quite sure how to tie this idea together or make it into a full post, so i'll just write this here.

you can intentionally take different actions in different timelines, by using quantum random numbers.^[1] this could be useful depending on your values. for example, let's say you think duplicate utopias are still good, but with diminishing added value compared to the value the first has compared to a multiverse without any. it might follow that you would want to, for example, donate a full sum of money to multiple alignment orgs, each in some percent of timelines, rather than dividing it evenly between them in every timeline. the goal of this would be to maximize the probability that at least some timelines end up with an aligned ASI, by taking different actions in different timelines

1. ^{^}

   not sure if it'll be intuitively clear to readers, so i'll elaborate here. let's say a quantum experiment is done where it produces one outcome (a) in half of timelines, and another outcome (b) in the other half. by precommiting to take action 1 in timelines where outcome (a) happens, and action 2 in timelines where outcome (b) happens, the result is that both actions happen, each in 50% of timelines.

   this can of course be generalized to more fine-grained percentages. e.g., if you repeat the experiment twice, you now have four possible outcome-combinations to divide up to 4 paths of action between.

(status: im newer here, this is a random thought i had, could be obvious to others, might also help when talking to outsiders about ai risk)

humans seem like a good example of an intelligence takeoff. for most of prehistory, species were following the same basic patterns repetitively (eating each other, trying to survive, etc.) 

then at some arbitrary point, one species either passed some threshold in intelligence, or maybe it just gained a pivotal intelligence-unrelated ability (such as opposable thumbs), or maybe it just found itself in the right situation (e.g the agricultural revolution is commonly explained by humans ending up in an environment better suited for plant growth).

and then it spiraled out of control to where we are now.

and in the future, this species is gonna create an even more powerful intelligence. this mirrors our own worries about AI creating a more powerful AI. 

sometimes people say that there's no evidence for AI doom because it hasn't been tested. humans might be moving evidence to such people when framed this way.

this might also have implications for how AI takeoff might go. it might be that there won't be some surprisingly increase in intelligence compared to earlier AIs - it could be more like the biointellegence takeoff, where it happens after some arbitrary-seeming conditions are met.