This is a special post for quick takes by Ben Pace. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.

The comments here are a storage of not-posts and not-ideas that I would rather write down than not.

14 comments, sorted by Click to highlight new comments since:

For too long, I have erred on the side of writing too much. 

The first reason I write is in order to find out what I think.

This often leaves my writing long and not very defensible.

However, editing the whole thing is so much extra work after I already did all the work figuring out what I think.

Sometimes it goes well if I just scrap the whole thing and concisely write my conclusion.

But typically I don't want to spend the marginal time.

Another reason my writing is too long is because I have extra thoughts I know most people won't find useful. 

But I've picked up a heuristic that says it's good to share actual thinking because sometimes some people find it surprisingly useful, so I hit publish anyway.

Nonetheless, I endeavor to write shorter.

So I think I shall experiment with cutting the bits off of comments that represent me thinking aloud, but aren't worth the space in the local conversation.

And I will put them here, as the dregs of my cognition. I shall hopefully gather data over the next month or two and find out whether they are in fact worthwhile.

I don't want to double the comment count I submit to Recent Discussion, so I'll just update this comment with the things I've cut.

12/06/2023 Comment on Originality vs. Correctness

It's fun to take the wins of one culture and apply them to the other, people are very shocked that you found some hidden value to be had (though it often isn't competitive value / legible to the culture). And if you manage to avoid some terrible decison people speak about how wise you are to have noticed.

(Those are the best cases, often of course people are like "this is odd, I'm going to pretend I didn't see this" and then move on.)

Hot take: The actual resolution to the simulation argument is that most advanced civilizations don't make loads of simulations.

Two things make this make sense:

  • Firstly, it only matters if they make unlawful simulations. If they make lawful simulations, then it doesn't matter whether you're in a simulation or a base reality, all of your decision theory and incentives are essentially the same, you want to take the same decisions in all of the universes. So you can make lots of lawful simulations, that's fine.
  • Secondly, they will strategically choose to not make too many unlawful simulations (to the level where the things inside are actually conscious). This is because to do so would induce anthropic uncertainty over themselves. Like, if the decision-theoretical answer is to not induce anthropic uncertainty over yourself about whether you're in a simulation, then by TDT everyone will choose not to make unlawful simulations.

I think this is probably wrong in lots of ways but I didn't stop to figure them out.

Your first point sounds like it is saying we are probably in a simulation, but not the sort that should influence our decisions, because it is lawful. I think this is pretty much exactly what Bostrom's Simulation Hypothesis is, so I think your first point is not an argument for the second disjunct of the simulation argument but rather for the third.

As for the second point, well, there are many ways for a simulation to be unlawful, and only some of them are undesirable--for example, a civilization might actually want to induce anthropic uncertainty in itself, if it is uncertainty about whether or not it is in a simulation that contains a pleasant afterlife for everyone who dies.

I don't buy that it makes sense to induce anthropic uncertainty. It makes sense to spend all of your compute to run emulations that are having awesome lives, but it doesn't make sense to cause yourself to believe false things.

I'm not sure it makes sense either, but I don't think it is accurately described as "cause yourself to believe false things." I think whether or not it makes sense comes down to decision theory. If you use evidential decision theory, it makes sense; if you use causal decision theory, it doesn't. If you use functional decision theory, or updateless decision theory, I'm not sure, I'd have to think more about it. (My guess is that updateless decision theory would do it insofar as you care more about yourself than others, and functional decision theory wouldn't do it even then.)

I just don’t think it’s a good decision to make, regardless of the math. If I’m nearing the end of the universe, I prefer to spend all my compute instead maximising fun / searching for a way out. Trying to run simulations to make it so I no longer know if I’m about to die seems like a dumb use of compute. I can bear the thought of dying dude, there’s better uses of that compute. You’re not saving yourself, you’re just intentionally making yourself confused because you’re uncomfortable with the thought of death.

Well, that wasn't the scenario I had in mind. The scenario I had in mind was: People in the year 2030 pass a law requiring future governments to make ancestor simulations with happy afterlives, because that way it's probable that they themselves will be in such a simulation. (It's like cryonics, but cheaper!) Then, hundreds or billions of years later, the future government carries out the plan, as required by law.

Not saying this is what we should do, just saying it's a decision I could sympathize with, and I imagine it's a decision some fraction of people would make, if they thought it was an option.

Thinking more, I think there are good arguments for taking actions that as a by-product induce anthropic uncertainty; these are the standard hansonian situation where you build lots of ems of yourself to do bits of work then turn them off. 

But I still don't agree with the people in the situation you describe because they're optimising over their own epistemic state, I think they're morally wrong to do that. I'm totally fine with a law requiring future governments to rebuild you / an em of you and give you a nice life (perhaps as a trade for working harder today to ensure that the future world exists), but that's conceptually analogous to extending your life, and doesn't require causing you to believe false things. You know you'll be turned off and then later a copy of you will be turned on, there's no anthropic uncertainty, you're just going to get lots of valuable stuff.

The relevant intuition to the second point there, is to imagine you somehow found out that there was only one ground truth base reality, only one real world, not a multiverse or a tegmark level 4 verse or whatever. And you're a civilization that has successfully dealt with x-risks and unilateralist action and information vulnerabilities, to the point where you have the sort of unified control to make a top-down decision about whether to make massive numbers of civilizations. And you're wondring whether to make a billion simulations.

And suddenly you're faced with the prospect of building something that will make it so you no longer know whether you're in the base universe. Someday gravity might get turned off because that's what your overlords wanted. If you pull the trigger, you'll never be sure that you weren't actually one of the simulated ones, because there's suddenly so many simulations.

And so you don't pull the trigger, and you remain confident that you're in the base universe.

This, plus some assumptions about all civilizations that have the capacity to do massive simulations also being wise enough to overcome x-risk and coordination problems so they can actually make a top-down decision here, plus some TDT magic whereby all such civilizations in the various multiverses and Tegmark levels can all coordinate in logical time to pick the same decision... leaves there being no unlawful simulations.

My crux here is that I don't feel much uncertainty about whether or not our overlords will start interacting with us (they won't and I really don't expect that to change), and I'm trying to backchain from that to find reasons why it makes sense.

My basic argument is that all civilizations that have the capability to make simulations that aren't true histories (but instead have lots of weird stuff happen in them) will all be philosophically sophisticated to collectively not do so, and so you can always expect to be in a true history and not have weird sh*t happen to you like in The Sims. The main counterargument here is to show that there are lots of civilizations that will exist with the powers to do this but lacking the wisdom to not do it. Two key examples that come to mind:

  • We build an AGI singleton that lacks important kinds of philosophical maturity, so makes lots of simulations that ruins the anthropic uncertainty for everyone else.
  • Civilizations at somewhere around our level get to a point where they can create massive numbers of simulations but haven't managed to create existential risks like AGI. Even while you might think our civilization is pretty close to AGI, I could imagine alternative civilizations that aren't, just like I could imagine alternative civilizations that are really close to making masses of ems but that aren't close enough to AGI. This feels like a pretty empirical question about whether such civilizations are possible and whether they can have these kinds of resources without causing an existential catastrophe / building singleton AGI.

One big reason why it makes sense is that the simulation is designed for the purpose of accurately representing reality.

Another big reason why (a version of it) makes sense is that the simulation is designed for the purpose of inducing anthropic uncertainty in someone at some later time in the simulation. e.g. if the point of the simulation is to make our AGI worry that it is in a simulation, and manipulate it via probable environment hacking, then the simulation will be accurate and lawful (i.e. un-tampered-with) until AGI is created.

I think "polluting the lake" by increasing the general likelihood of you (and anyone else) being in a simulation is indeed something that some agents might not want to do, but (a) it's a collective action problem, and (b) plenty of agents won't mind it that much, and (c) there are good reasons to do it even if it has costs. I admit I am a bit confused about this though, so thank you for bringing it up, I will think about it more in the coming months.

Another big reason why (a version of it) makes sense is that the simulation is designed for the purpose of inducing anthropic uncertainty in someone at some later time in the simulation. e.g. if the point of the simulation is to make our AGI worry that it is in a simulation, and manipulate it via probable environment hacking, then the simulation will be accurate and lawful (i.e. un-tampered-with) until AGI is created.

Ugh, anthropic warfare, feels so ugly and scary. I hope we never face that sh*t.

I've been thinking lately that picturing an AI catastrophe is helped a great deal by visualising a world where critical systems in society are performed by software. I was spending a while trying to summarise and analyse Paul's "What Failure Looks Like", which lead me this way. I think that properly imagining such a world is immediately scary, because software can deal with edge cases badly, like automated market traders causing major crashes, so that's already a big deal. Then you add ML in, and can talk about how crazy it is to hand critical systems over to code we do not understand and cannot make simple adjustments to, then you're already hitting catastrophes. Once you then argue that ML can become superintelligent then everything goes from "global catastrophe" to "obvious end of the world", but the first steps are already pretty helpful.

While Paul's post helps a lot, it still takes a fair bit of effort for me to concretely visualise the scenarios he describes, and I would be excited for people to take the time to detail what it would look like to hand critical systems over to software – for which systems would this happen, why would we do it, who would be the decision-makers, what would it feel like from the average citizen's vantage point, etc. A smaller version of Hanson's Age of Em project, just asking the question "Which core functions in society (food, housing, healthcare, law enforcement, governance, etc) are amenable to tech companies building solutions for, and what would it look like for society to transition to 1%, 10%, 50% and 90% of core functions to be automated with 1) human-coded software 2) machine learning 3) human-level general AI?"