Research analyst at Open Philanthropy. All opinions are my own.
Lukas_Finnveden
Karma: 1,050
I really like the proposed calibration game! One thing I’m curious about is whether real-world evidence more often looks like a likelihood ratio or like something else (e.g. pointing towards a specific probability being correct). Maybe you could see this from the structure of priors+likelihoodratios+posteriors in the calibration game — e.g. check whether the long-run top-scorers likelihood ratios correlated more or less than their posterior probabilities.
(If someone wanted to build this: one option would be to start with pastcasting and then give archived articles or wikipedia pages as evidence. Maybe a sophisticated version could let you start out with an old relevant wikipedia page, and then see a wikipedia page much closer to the resolution date as extra evidence.)
And it would probably be a huge mistake to seek out an adderall prescription.
...unless you have other reasons to believe that an Adderall prescription might be good for you. Saliently: if you have adhd symptoms.
Depends on how much of their data they’d have to back up like this. If every bit ever produced or operated on instead had to be be 25 bits — that seems like a big fitness hit. But if they’re only this paranoid about a few crucial files (e.g. the minds of a few decision-makers), then that’s cheap.
And there’s another question about how much stability contributes to fitness. In humans, cancer tends to not be great for fitness. Analogously, it’s possible that most random errors in future civilizations would look less like slowly corrupting values and more like a coordinated whole splintering into squabbling factions that can easily be conquered by a unified enemy. If so, you might think that an institution that cared about stopping value-drift and an instiution that didn’t would both have a similarly large interest in preventing random errors.
Also, by the same token, even if there is a “singleton” at some relatively early time, mightn’t it prefer to take on a non-negligible risk of value drift later in time if it means being able to, say, 10x its effective storage capacity in the meantime?
The counter-argument is that it will be super rich regardless, so it seems like satiable value systems would be happy to spend a lot on preventing really bad events from happening with small probability. Whereas instabiable value systems would notice that most resources are in the cosmos, and so also be obsessed with avoiding unwanted value drift. But yeah, if the values contain a pure time preference, and/or doesn’t care that much about the most probable types of value drift, then it’s possible that they wouldn’t deem the investment worth it.
This is a great question. I think the answer depends on the type of storage you’re doing.
If you have a totally static lump of data that you want to encode in a harddrive and not touch for a billion years, I think the challenge is mostly in designing a type of storage unit that won’t age. Digital error correction won’t help if your whole magnetism-based harddrive loses its magnetism. I’m not sure how hard this is.
But I think more realistically, you want to use a type of hardware that you regularly use, regularly service, and where you can copy the information to a new harddrive when one is about to fail. So I’ll answer the question in that context.
As an error rate, let’s use the failure rate of 3.7e-9 per byte per month ~= 1.5e-11 per bit per day from this stack overflow reply. (It’s for RAM, which I think is more volatile than e.g. SSD storage, and certainly not optimised for stability, so you could probably get that down a lot.)
Let’s use the following as an error correction method: Each bit is represented by N bits; for any computation the computer does, it will use the majority vote of the N bits; and once per day,[1] each bit is reset to the majority vote of its group of bits.
If so...
for N=1, the probability that a bit is stable for 1e9 years is ~exp(-1.5e-11*365*1e9)=0.4%. Yikes!
for N=3, the probability that 2 bit flips happen in a single day is ~3*(1.5e-11)^2 and so the probability that a group of bits is stable for 1e9 years is ~exp(-3*(1.5e-11)^2*365*1e9)=1-2e-10. Much better, but there will probably still be a million errors in that petabyte of data.
for N=5, the probability that 3 bit flips happen in a single day is ~(5 choose 2)*(1.5e-11)^3 and so the probability that the whole petabyte of data is safe for 1e9 years is ~99.99%. And so on this scheme, it seems that 5 petabytes of storage is enough to make 1 petabyte stable for a billion years.
Based on the discussion here, I think the errors in doing the majority-voting calculations are negligible compared to the cosmic ray calculations. At least if you do it cleverly so that you don’t get too many correlations and ruin your redundance (which there are ways to do according to results on error correcting computations — though I’m not sure if they might require some fixed amount of extra storage space to do this, in which case you might need N somewhat greater than 5).
Now this scheme requires that you have a functioning civilization that can provide electricity for the computer, that can replace the hardware when it starts failing, and stuff — but that’s all things that we wanted to have anyway. And any essential component of that civilization can run on similarly error-corrected hardware.
And to account for larger-scale problems than cosmic rays (e.g. local earthquake throws harddrive to the ground and shatters it, or you accidentally erase a file when you were supposed to make a copy of it), you’d probably want backup copies of the petabyte on different places across the Earth, which you replaced each time something happened to one of them. If there’s an 0.1% chance of that happening in any one day (corresponding to once/3 years, which seems like an overestimate if you’re careful), and you immediately notice it and replace the copy within a day, and you have 5 copies in total, the probability that one of them keeps working at all times is ~exp(-(0.001)^5*365*1e9)~=99.96%. So combined with the previous 5, that’d be a multiple of 5*5=25.
This felt enlightening. I’ll add a link to this comment from the doc.
- ^
Using a day here rather than an hour or a month isn’t super-motivated. If you reset things very frequently, you might interfere with normal use of the computer, and errors in the resetting-operation might start to dominate the errors from cosmic rays. But I think a day should be above the threshold where that’s much of an issue.
I’m not sure how literally you mean “disprove”, but at it’s face, “assume nothing is related to anything until you have proven otherwise” is a reasoning procedure that will never recommend any action in the real world, because we never get that kind of certainty. When humans try to achieve results in the real world, heuristics, informal arguments, and looking at what seems to have worked ok in the past are unavoidable.
Global poverty probably have slower diminishing marginal returns, yeah. Unsure about animal welfare. I was mostly thinking about longtermist causes.
Re 80,000 Hours: I don’t know exactly what they’ve argued, but I think “very valuable” is compatible with logarithmic returns. There are also diminishing marginal returns to direct workers in any given cause, so logarithmic returns on money doesn’t mean that money becomes unimportant compared to people, or anything like that.
Because utility and integrity are wholly independent variables, so there is no reason for us to assume a priori that they will always correlate perfectly. So if we wish to believe that integrity and expected value correlated for SBF, then we must show it. We must actually do the math.
This feels a bit unfair when people (i) have argued that utility and integrity will correlate strongly in practical cases (why use “perfectly” as your bar?), and (ii) that they will do so in ways that will be easy to underestimate if you just “do the math”.
You might think they’re mistaken, but some of the arguments do specifically talk about why the “assume 0 correlation and do the math”-approach works poorly, so if you disagree it’d be nice if you addressed that directly.
Because a double-or-nothing coin-flip scales; it doesn’t stop having high EV when we start dealing with big bucks.
Risky bets aren’t themselves objectionable in the way that fraud is, but to just address this point narrowly: Realistic estimates puts risky bets at much worse EV when you control a large fraction of the altruistic pool of money. I think a decent first approximation is that EA’s impact scales with the logarithm of its wealth. If you’re gambling a small amount of money, that means you should be ~indifferent to 50⁄50 double or nothing (note that even in this case it doesn’t have positive EV). But if you’re gambling with the majority of wealth that’s predictably committed to EA causes, you should be much more scared about risky bets.
(Also in this case the downside isn’t “nothing” — it’s much worse.)
conflicts of interest in grant allocation, work place appointments should be avoided
Worth flagging: Since there are more men than women in EA, I would expect a greater fraction of EA women than EA men to be in relationships with other EAs. (And trying to think of examples off the top of my head supports that theory.) If this is right, the policy “don’t appoint people for jobs where they will have conflicts of interest” would systematically disadvantage women.
(By contrast, considering who you’re already in a work-relationship with when choosing who to date wouldn’t have a systematic effect like that.)
My inclination here would be to (as much as possible) avoid having partners make grant/job-appointment decisions about their partners. But that if someone seems to be the best for a job/grant (from the perspective of people who aren’t their partner), to not deny them that just because it would put them in a position closer to their partner.
(It’s possible that this is in line with what you meant.)
Yeah, I agree that multipolar dynamics could prevent lock-in from happening in practice.
I do think that “there is a non-trivial probability that a dominant institution will in fact exist”, and also that there’s a non-trivial probability that a multipolar scenario will either
(i) end via all relevant actors agreeing to set-up some stable compromise institution(s), or
(ii) itself end up being stable via each actor making themselves stable and their future interactions being very predictable. (E.g. because of an offence-defence balance strongly favoring defence.)
...but arguing for that isn’t really a focus of the doc.
(And also, a large part of why I believe they might happen is that they sound plausible enough, and I haven’t heard great arguments for why we should be confident in some particular alternative. Which is a bit hard to forcefully argue for.)
If re-running evolution requires simulating the weather and if this is computationally too difficult then re-running evolution may not be a viable path to AGI.
There are many things that prevent us from literally rerunning human evolution. The evolution anchor is not a proof that we could do exactly what evolution did, but instead an argument that if something as inefficient as evolution spit out human intelligence with that amount of compute, surely humanity could do it if we had a similar amount of compute. Evolution is very inefficient — it has itself been far less optimized than the creatures it produces.
(I’d have more specific objections to the idea that chaos-theory-in-weather in particular would be an issue: I think that a weather-distribution approximated with a different random generation procedure would be as likely to produce human intelligence as a weather distribution generated by Earth’s precise chaotic behavior. But that’s not very relevant, because there would be far bigger differences between Earthly evolution and what-humans-would-do-with-1e40-FLOP than the weather.)
For instance we might get WBEs only in hypothetical-2080 but get superintelligent LLMs in 2040, and the people using superintelligent LLMs make the world unrecognisably different by 2042 itself.
I definitely don’t just want to talk about what happens / what’s feasible before the world becomes unrecognisably different. It seems pretty likely to me that lock-in will only become feasible after the world has become extremely strange. (Though this depends a bit on details of how to define “feasible”, and what we count as the start-date of lock-in.)
And I think that advanced civilizations that tried could eventually become very knowledgable about how to create AI with a wide variety of properties, which is why I feel ok with the assumption that AIs could be made similar to humans in some ways without being WBEs.
(In particular, the arguments in this document are not novel suggestions for how to succeed with alignment in a realistic scenario with limited time! That still seems like a hard problem! C.f. my response to Michael Plant.)
Chaos theory is about systems where tiny deviations in initial conditions cause large deviations in what happens in the future. My impression (though I don’t know much about the field) is that, assuming some model of a system (e.g. the weather), you can prove things about how far ahead you can predict the system given some uncertainty (normally about the initial conditions, though uncertainty brought about by limited compute that forces approximations should work similarly). Whether the weather corresponds to any particular model isn’t really susceptible to proofs, but that question can be tackled by normal science.
Quoting from the post:
Thus, we suspect that an adequate solution to AI alignment could be achieved given sufficient time and effort. (Though whether that will actually happen is a different question, not addressed since our focus is on feasibility rather than likelihood.)
AI doomers tend to agree with this claim. See e.g. Eliezer in list of lethalities:
None of this is about anything being impossible in principle. The metaphor I usually use is that if a textbook from one hundred years in the future fell into our hands, containing all of the simple ideas that actually work robustly in practice, we could probably build an aligned superintelligence in six months. (...) What’s lethal is that we do not have the Textbook From The Future telling us all the simple solutions that actually in real life just work and are robust; we’re going to be doing everything with metaphorical sigmoids on the first critical try. No difficulty discussed here about AGI alignment is claimed by me to be impossible—to merely human science and engineering, let alone in principle—if we had 100 years to solve it using unlimited retries, the way that science usually has an unbounded time budget and unlimited retries. This list of lethalities is about things we are not on course to solve in practice in time on the first critical try; none of it is meant to make a much stronger claim about things that are impossible in principle.
Thanks Lizka. I think about section 0.0 as being a ~1-page summary (in between the 1-paragraph summary and the 6-page summary) but I could have better flagged that it can be read that way. And your bullet point summary is definitely even punchier.
Thanks!
You’ve assumed from the get go that AIs will follow similar reinforcement-learning like paradigms like humans and converge on similar ontologies of looking at the world as humans. You’ve also assumed these ontologies will be stable—for instance a RL agent wouldn’t become superintelligent, use reasoning and then decide to self modify into something that is not an RL agent.
Something like that, though I would phrase it as relying on the claim that it’s feasible to build AI systems like that, since the piece is about the feasibility of lock-in. And in that context, the claim seems pretty safe to me. (Largely because we know that humans exist.)
You’ve assumed laws of physics as we know them today are constraints on things like computation and space colonization and oversight and alignment processes for other AIs.
Yup, sounds right.
Does this assume a clean separation between two kinds of processes—those that can be predicted and those that can’t?
That’s a good question. I wouldn’t be shocked if something like this was roughly right, even if it’s not exactly right. Let’s imagine the situation from the post, where we have an intelligent observer with some large amount of compute that gets to see the paths of lots of other civilizations built by evolved species. Now let’s imagine a graph where the x-axis has some increasing combination of “compute” and “number of previous examples seen”, and the y-axis has something like “ability to predict important events”. At first, the y-value would probably go up pretty fast with greater x, as the observer get a better sense of what the distribution of outcomes are. But on our understanding of chaos theory, it’s ability to predict e.g. the weather years in advance would be limited even at astoundingly large values of compute+knowledge of what the distribution is like. And since chaotic processes affect important real-world events in various ways (e.g. the genes of new humans seem similarly random as the weather, and that has huge effects), it seems plausible that our imagined graph would asymptote towards some limit of what’s predictable.
And that’s not even bringing up fundamental quantum effects, which are fundamentally unpredictable from our perspective. (With a many-worlds interpretation, they might be predictable in the sense that all of them will happen. But that still lets us make interesting claims about “fractions of everett branches”, which seems pretty interchangeable with “probabilities of events”.)
In any case, I don’t think this impinges much on the main claims in the doc. (Though if I was convinced that the picture above was wildly wrong, I might want to give a bit of extra thought to what’s the most convenient definition of lock-in.)
I broadly agree with this. For the civilizations that want to keep thinking about their values or the philosophically tricky parts of their strategy, there will be an open question about how convergent/correct their thinking process is (although there’s lots you can do to make it more convergent/correct — eg. redo it under lots of different conditions, have arguments be reviewed by many different people/AIs, etc).
And it does seem like all reasonable civilizations should want to do some thinking like this. For those civilizations, this post is just saying that other sources of instability could be removed (if they so chose, and insofar as that was compatible with the intended thinking process).
Also, separately, my best guess is that competent civilizations (whatever that means) that were aiming for correctness would probably succeed (at least in areas were correctness is well defined). Maybe by solving metaphilosophy and doing that, maybe because they took lots of precautions like mentioned above, maybe just because it’s hard to get permanently stuck at incorrect beliefs if lots of people are dedicated to getting things right, have all the time and resources in the world, and are really open-minded. (If they’re not open-minded but feel strongly attached to keeping their current views, then I become more pessimistic.)
But even if a civilization was willing to take this extreme step, I’m not sure how you’d design a filter that could reliably detect and block all “reasoning” that might exploit some flaw in your reasoning process.
By being unreasonably conservative. Most AIs could be tasked with narrowly doing their job, a few with pushing forward technology/engineering, none with doing anything that looks suspiciously like ethics/philosophy. (This seems like a bad idea.)
And tags / wiki entries.
We used the geometric mean of the samples with the minimum and maximum removed to better deal with extreme outliers, as described in our previous post
I don’t see how that’s consistent with:
What is the probability that Russia will use a nuclear weapon in Ukraine in the next MONTH?
Aggregate probability: 0.0859 (8.6%)
All probabilities: 0.27, 0.04, 0.02, 0.001, 0.09, 0.08, 0.07
What is the probability that Russia will use a nuclear weapon in Ukraine in the next YEAR?
Aggregate probability: 0.2294 (23%)
All probabilities: 0.38, 0.11, 0.11, 0.005, 0.42, 0.2, 0.11
I get that the first of those should be 0.053. Haven’t run the numbers on the latter, but pretty sure the geometric mean should be smaller than 23% from eyeballing it. (I also haven’t run the numbers on other aggregated numbers in this post.)
If AGI systems had goals that were cleanly separated from the rest of their cognition, such that they could learn and self-improve without risking any value drift (as long as the values-file wasn’t modified), then there’s a straightforward argument that you could stabilise and preserve that system’s goals by just storing the values-file with enough redundancy and digital error correction.
So this would make section 6 mostly irrelevant. But I think most other sections remain relevant, insofar as people weren’t already convinced that being able to build stable AGI systems would enable world-wide lock-in.
I was mostly imagining this scenario as I was writing, so when relevant, examples/terminology/arguments will be taylored for that, yeah.