# Andrew_Critch(Andrew Critch)

Karma: 639

This is Dr. Andrew Critch’s professional LessWrong account. Andrew is currently a full-time Research Scientist at the Center for Human-Compatible AI (CHAI) at UC Berkeley, and spends around a ½ day per week volunteering for the Berkeley Existential Risk initiative. He earned his Ph.D. in mathematics at UC Berkeley studying applications of algebraic geometry to machine learning models. During that time, he cofounded the Center for Applied Rationality and SPARC. Dr. Critch has been offered university faculty and research positions in mathematics, mathematical biosciences, and philosophy, worked as an algorithmic stock trader at Jane Street Capital’s New York City office, and as a Research Fellow at the Machine Intelligence Research Institute. His current research interests include logical uncertainty, open source game theory, and mitigating race dynamics between companies and nations in AI development.

• Nice post! I think something closer to would be a better multiplier than two. Reason:

Instead of minimizing the upper bound of total effort (b^2d−1)/​(b-1), it makes sense to also consider the lower bound, (bd−1)/​(b-1), which is achieved when d is a power of b. We can treat the “expected” effort (e.g., if you have a uniform improper prior on ) as landing in the middle of these two numbers, i.e.,

This is minimized where which approaches b=1+√2 for d large. If you squint at your seesaw graphs and imagine a line “through the middle” of the peaks and troughs, I think you can see it bottoming out at around 2.4.

• Sorry for the slow reply!

I feel like you are lumping together things like “bargaining in a world with many AIs representing diverse stakeholders” with things like “prioritizing actions on the basis of how they affect the balance of power.”

Yes, but not a crux for my point. I think this community has a blind/​blurry spot around both of those things (compared to the most influential elites shaping the future of humanity). So, the thesis statement of the post does not hinge on this distinction, IMO.

I would prefer keep those things separate.

Yep, and in fact, for actually diagnosing the structure of the problem, I would prefer to subdivide further into three things and not just two:

1. Thinking about how power dynamics play out in the world;

2. Thinking about what actions are optimal*, given (1); and

3. Choosing optimal* actions, given (2) (which, as you say, can involve actions chosen to shift power balances)

My concern is that the causal factors laid out in this post have lead to correctable weaknesses in all three of these areas. I’m more confident in the claim of weakness (relative to skilled thinkers in this area, not average thinkers) than any particular causal story for how the weakness formed. But, having drawn out the distinction among 1-3, I’ll say that the following mechanism is probably at play in a bunch of people:

a) people are really afraid of people manipulated;

b) they see/​experience (3) as an instance of being manipulated and therefore have strong fear reactions around it (or disgust, or anger, or anxiety);

c) their avoidance reactions around (3) generalize to avoiding (1) and (2).

d) point (c) compounds with the other causal factors in the OP to lead to too-much-avoidance-of-thought around power/​bargaining.

There are of course specific people who are exceptions to this concern. And, I hear you that you do lots of (1) and (2) while choosing actions based on a version of optimal* defined in terms of “win-wins”. (This is not an update for me, because I know that you personally think about bargaining dynamics.)

However, my concern is not about you-specifically. Who exactly is about, you might ask? I’d say “the average lesswrong reader” or “the average AI researcher interested in AI alignment”.

For example, “Politics is the mind-killer” is mostly levied against doing politics, not thinking about politics as someonething that someone else might do (thereby destroy the world).

Yes, but not a crux to the point I’m trying to make. I already noted in the post that PMK is was not trying to make people think about politics; in fact, I included a direct quote to that effect: “The PMK post does not directly advocate for readers to avoid thinking about politics; in fact, it says “I’m not saying that I think we should be apolitical, or even that we should adopt Wikipedia’s ideal of the Neutral Point of View.” ” My concern, as noted in the post, is that the effects of PMK (rather than its intentions) may have been somewhat crippling:

[OP] However, it also begins with the statement “People go funny in the head when talking about politics”. If a person doubts their own ability not to “go funny in the head”, the PMK post — and concerns like it — could lead them to avoid thinking about or engaging with politics as a way of preventing themselves from “going funny”.

I also agree with the following comparison you made to mainstream AI/​ML, but it’s also not a crux for the point I’m trying to make:

it seems to me that rationalist and EA community think about AI-AI bargaining and costs from AI-AI competition much more than the typical AI researchers, as measured by e.g. fraction of time spent thinking about those problems, fraction of writing that is about those problems, fraction of stated research priorities that involve those problems, and so on. This is all despite outlier technical beliefs suggesting an unprecedentedly “unipolar” world during the most important parts of AI deployment (which I mostly disagree with).

My concern is not that our community is under-performing the average AI/​ML researcher in thinking about the future — as you point out, we are clearly over-performing. Rather, the concern is that we are underperforming the forces that will actually shape the future, which are driven primarily by the most skilled people who are going around shifting the balance of power. Moreover, my read on this community is that it mostly exhibits a disdainful reaction to those skills, both in specific (e.g., if I called out specific people who have them) and in general (if I call them out in the abstract, as I have here).

Here’s a another way of laying out what I think is going on:

A = «anxiety/​fear/​disgust/​anger around being manipulated»

B = «filter-bubbling around early EA narratives designed for institution-building, single, single-stakeholder AI alignment»

C = «commitment to the art-of-rationality/​thinking»

S = «skill at thinking about power dynamics»

D = «disdain for people who exhibit S»

Effect 1: A increases C (this is healthy).

Effect 2: C increases S (which is probably why out community it out-performing mainstream AI/​ML).

Effect 3: A decreases S in a bunch of people (not all people!), specifically, people who turn anxiety into avoidance-of-the-topic.

Effect 4: Effects 1-3 make it easy for a filter-bubble to form that ignores power dynamics among and around powerful AI systems and counts on single-stakeholder AI alignment to save the world with one big strong power-dynamic instead of a more efficient/​nuanced wielding of power.

The solution to this problem is not to decrease C, from which we derive our strength, but to mitigate Effect 3 by getting A to be more calibrated /​ less triggered. Around AI specifically, this requires holding space in discourse for thinking and writing about power-dynamics in multi-stakeholder scenarios.

Hopefully this correction can be made without significantly harming efforts to diversify highly focussed efforts on alignment, such as yours. E.g., I’m still hoping like 10 people will go work for you at ARC, as soon as you want to expand to that size, in large part because I know you personally think about bargaining dynamics and are mulling them over in the background while you address alignment. [Other readers: please consider this an endorsement to go work for Paul if he wants you on his team!]

# Power dy­nam­ics as a blind spot or blurry spot in our col­lec­tive world-mod­el­ing, es­pe­cially around AI

1 Jun 2021 18:45 UTC
166 points
• > Failure mode: When B-cultured entities invest in “having more influence”, often the easiest way to do this will be for them to invest in or copy A’-cultured-entities/​processes. This increases the total presence of A’-like processes in the world, which have many opportunities to coordinate because of their shared (power-maximizing) values. Moreover, the A’ culture has an incentive to trick the B culture(s) into thinking A’ will not take over the world, but eventually, A’ wins.

> In other words, the humans and human-aligned institutions not collectively being good enough at cooperation/​bargaining risks a slow slipping-away of hard-to-express values and an easy takeover of simple-to-express values (e.g., power-maximization).

This doesn’t feel like other words to me, it feels like a totally different claim.

Hmm, perhaps this is indicative of a key misunderstanding.

For example, natural monopolies in the production web wouldn’t charge each other marginal costs, they would charge profit-maximizing profits.

Why not? The third paragraph of the story indicates that: “Companies closer to becoming fully automated achieve faster turnaround times, deal bandwidth, and creativity of negotiations.” In other words, at that point it could certainly happen that two monopolies would agree to charge each other lower cost if it benefitted both of them. (Unless you’d count that as instance of “charging profit-maximizing costs”?) The concern is that the subprocesses of each company/​institution that get good at (or succeed at) bargaining with other institutions are subprocesses that (by virtue of being selected for speed and simplicity) are less aligned with human existence than the original overall company/​institution, and that less-aligned subprocess grows to take over the institution, while always taking actions that are “good” for the host institution when viewed as a unilateral move in an uncoordinated game (hence passing as “aligned”).

At this point, my plan is try to consolidate what I think the are main confusions in the comments of this post, into one or more new concepts to form the topic of a new post.

• > My prior (and present) position is that reliability meeting a certain threshold, rather than being optimized, is a dominant factor in how soon deployment happens.

I don’t think we can get to convergence on many of these discussions, so I’m happy to just leave it here for the reader to think through.

Yeah I agree we probably can’t reach convergence on how alignment affects deployment time, at least not in this medium (especially since a lot of info about company policies /​ plans /​ standards are covered under NDAs), so I also think it’s good to leave this question about deployment-time as a hanging disagreement node.

I’m reading this (and your prior post) as bids for junior researchers to shift what they focus on. My hope is that seeing the back-and-forth in the comments will, in expectation, help them decide better.

Yes to both points; I’d thought of writing a debate dialogue on this topic trying to cover both sides, but commenting with you about it is turning out better I think, so thank for that!

• > Both [cultures A and B] are aiming to preserve human values, but within A, a subculture A’ develops to favor more efficient business practices (nihilistic power-maximizing) over preserving human values.

I was asking you why you thought A’ would effectively outcompete B (sorry for being unclear). For example, why do people with intrinsic interest in power-maximization outcompete people who are interested in human flourishing but still invest their money to have more influence in the future?

Ah! Yes, this is really getting to the crux of things. The short answer is that I’m worried about the following failure mode:

Failure mode: When B-cultured entities invest in “having more influence”, often the easiest way to do this will be for them to invest in or copy A’-cultured-entities/​processes. This increases the total presence of A’-like processes in the world, which have many opportunities to coordinate because of their shared (power-maximizing) values. Moreover, the A’ culture has an incentive to trick the B culture(s) into thinking A’ will not take over the world, but eventually, A’ wins.

(Here’s, I’m using the word “culture” to encode a mix of information subsuming utility functions, beliefs, and decision theory, cognitive capacities, and other features determining the general tendencies of an agent or collective.)

Of course, an easy antidote to this failure mode is to have A or B win instead of A’, because A and B both have some human values other than power-maximizing. The problem is that this whole situation is premised on a conflict between A and B over which culture should win, and then the following observation applies:

• Wei Dai has suggested that groups with unified values might outcompete groups with heterogeneous values since homogeneous values allow for better coordination, and that AI may make this phenomenon more important.

In other words, the humans and human-aligned institutions not collectively being good enough at cooperation/​bargaining risks a slow slipping-away of hard-to-express values and an easy takeover of simple-to-express values (e.g., power-maximization). This observation is slightly different from observations that “simple values dominate engineering efforts” as seen in stories about singleton paperclip maximizers. A key feature of the Production Web dynamic is now just that it’s easy to build production maximizers, but that it’s easy to accidentally cooperate on building a production-maximizing systems that destroy both you and your competitors.

This feels inconsistent with many of the things you are saying in your story, but

Thanks for noticing whatever you think are the inconsistencies; if you have time, I’d love for you to point them out.

I might be misunderstanding what you are saying and it could be that some argument like like Wei Dai’s is the best way to translate your concerns into my language.

This seems pretty likely to me. The bolded attribution to Dai above is a pretty important RAAP in my opinion, and it’s definitely a theme in the Production Web story as I intend it. Specifically, the subprocesses of each culture that are in charge of production-maximization end up cooperating really well with each other in a way that ends up collectively overwhelming the original (human) cultures. Throughout this, each cultural subprocess is doing what its “host culture” wants it to do from a unilateral perspective (work faster /​ keep up with the competitor cultures), but the overall effect is destruction of the host cultures (a la Prisoner’s Dilemma) by the cultural subprocesses.

If I had to use alignment language, I’d say “the production web overall is misaligned with human culture, while each part of the web is sufficiently well-aligned with the human entit(ies) who interact with it that it is allowed to continue operating”. Too low of a bar for “allowed to continue operating” is key to the failure mode, of course, and you and I might have different predictions about what bar humanity will actually end up using at roll-out time. I would agree, though, that conditional on a given roll-out date, improving E[alignment_tech_quality] on that date is good and complimentary to improving E[cooperation_tech_quality] on that date.

Did this get us any closer to agreement around the Production Web story? Or if not, would it help to focus on the aforementioned inconsistencies with homogenous-coordination-advantage?

• Thanks for the pointer to grace2020whose! I’ve added it to the original post now under “successes in our agent-agnostic thinking”.

But I also think the AI safety community has had important contributions on this front.

For sure, that is the point of the “successes” section. Instead of “outside the EA /​ rationality /​ x-risk meme-bubbles, lots of AI researchers think about agent-agnostic processes” I should probably have said “outside the EA /​ rationality /​ x-risk meme-bubbles, lots of AI researchers think about agent-agnostic processes, and to my eye there should be more communication across the boundary of that bubble.”

• Thanks for this synopsis of your impressions, and +1 to the two points you think we agree on.

I also read the post as also implying or suggesting some things I’d disagree with:

As for these, some of them are real positions I hold, while some are not:

• That there is some real sense in which “cooperation itself is the problem.”

I don’t hold that view. I the closest view I hold is more like: “Failing to cooperate on alignment is the problem, and solving it involves being both good at cooperation and good at alignment.”

• Relatedly, that cooperation plays a qualitatively different role than other kinds of cognitive enhancement or institutional improvement.

I don’t hold the view you attribute to me here, and I agree wholesale with the following position, including your comparisons of cooperation with brain enhancement and improving belief accuracy:

I think that both cooperative improvements and cognitive enhancement operate by improving people’s ability to confront problems, and both of them have the downside that they also accelerate the arrival of many of our future problems (most of which are driven by human activity). My current sense is that cooperation has a better tradeoff than some forms of enhancement (e.g. giving humans bigger brains) and worse than others (e.g. improving the accuracy of people’s and institution’s beliefs about the world).

… with one caveat: some beliefs are self-fulfilling, such as cooperation/​defection. There are ways of improving belief accuracy that favor defection, and ways that favor cooperation. Plausibly to me, the ways of improving belief accuracy that favor defection are worse that mo accuracy improvement at all. I’m particularly firm in this view, though; it’s more of a hedge.

• That the nature of the coordination problem for AI systems is qualitatively different from the problem for humans, or somehow is tied up with existential risk from AI in a distinctive way. I think that the coordination problem amongst reasonably-aligned AI systems is very similar to coordination problems amongst humans, and that interventions that improve coordination amongst existing humans and institutions (and research that engages in detail with the nature of existing coordination challenges) are generally more valuable than e.g. work in multi-agent RL or computational social choice.

I do hold this view! Particularly the bolded part. I also agree with the bolded parts of your counterpoint, but I think you might be underestimating the value of technical work (e.g., CSC, MARL) directed at improving coordination amongst existing humans and human institutions.

I think blockchain tech is a good example of an already-mildly-transformative technology for implementing radically mutually transparent and cooperative strategies through smart contracts. Make no mistake: I’m not claiming blockchain tehc is going to “save the world”; rather, it’s changing the way people cooperate, and is doing so as a result of a technical insight. I think more technical insights are in order to improve cooperation and/​or the global structure of society, and it’s worth spending research efforts to find them.

Reminder: this is not a bid for you personally to quit working on alignment!

• That this story is consistent with your prior arguments for why single-single alignment has low (or even negative) value. For example, in this comment you wrote “reliability is a strongly dominant factor in decisions in deploying real-world technology, such that to me it feels roughly-correctly to treat it as the only factor.” But in this story people choose to adopt technologies that are less robustly aligned because they lead to more capabilities. This tradeoff has real costs even for the person deploying the AI (who is ultimately no longer able to actually receive any profits at all from the firms in which they are nominally a shareholder). So to me your story seems inconsistent with that position and with your prior argument. (Though I don’t actually disagree with the framing in this story, and I may simply not understand your prior position.)

My prior (and present) position is that reliability meeting a certain threshold, rather than being optimized, is a dominant factor in how soon deployment happens. In practice, I think the threshold by default will not be “Reliable enough to partake in a globally cooperative technosphere that preserves human existence”, but rather, “Reliable enough to optimize unilaterally for the benefits of the stakeholders of each system, i.e., to maintain or increase each stakeholder’s competitive advantage.” With that threshold, there easily arises a RAAP racing to the bottom on how much human control/​safety/​existence is left in the global economy. I think both purely-human interventions (e.g., talking with governments) and sociotechnical interventions (e.g., inventing cooperation-promoting tech) can improve that situation. This is not to say “cooperation is all you need”, any more than I than I would say “alignment is all you need”.

• The previous story tends to frame this more as a failure of humanity’s coordination, while this one frames it (in the title) as a failure of intent alignment. It seems like both of these aspects greatly increase the plausibility of the story, or in other words, if we eliminated or made significantly less bad either of the two failures, then the story would no longer seem very plausible.

Yes, I agree with this.

A natural next question is then which of the two failures would be best to intervene on, that is, is it more useful to work on intent alignment, or working on coordination? I’ll note that my best guess is that for any given person, this effect is minor relative to “which of the two topics is the person more interested in?”, so it doesn’t seem hugely important to me.

Yes! +10 to this! For some reason when I express opinions of the form “Alignment isn’t the most valuable thing on the margin”, alignment-oriented folks (e.g., Paul here) seem to think I’m saying you shouldn’t work on alignment (which I’m not), which triggers a “Yes, this is the most valuable thing” reply. I’m trying to say “Hey, if you care about AI x-risk, alignment isn’t the only game in town”, and staking some personal reputation points to push against the status quo where almost-everyone x-risk oriented will work on alignment almost-nobody x-risk-oriented will work on cooperation/​coordination or multi/​multi delegation.

Perhaps I should start saying “Guys, can we encourage folks to work on both issues please, so that people who care about x-risk have more ways to show up and professionally matter?”, and maybe that will trigger less pushback of the form “No, alignment is the most important thing”…

• I think that the biggest difference between us is that I think that working on single-single alignment is the easiest way to make headway on that issue, whereas you expect greater improvements from some categories of technical work on coordination

Yes.

(my sense is that I’m quite skeptical about most of the particular kinds of work you advocate

That is also my sense, and a major reason I suspect multi/​multi delegation dynamics will remain neglected among x-risk oriented researchers for the next 3-5 years at least.

If you disagree, then I expect the main disagreement is about those other sources of overhead

Yes, I think coordination costs will by default pose a high overhead cost to preserving human values among systems with the potential to race to the bottom on how much they preserve human values.

> I think I disagree with you on the tininess of the advantage conferred by ignoring human values early on during a multi-polar take-off. I agree the long-run cost of supporting humans is tiny, but I’m trying to highlight a dynamic where fairly myopic/​nihilistic power-maximizing entities end up quickly out-competing entities with other values, due to, as you say, bargaining failure on the part of the creators of the power-maximizing entities.

Could you explain the advantage you are imagining?

Yes. Imagine two competing cultures A and B have transformative AI tech. Both are aiming to preserve human values, but within A, a subculture A’ develops to favor more efficient business practices (nihilistic power-maximizing) over preserving human values. The shift is by design subtle enough not to trigger leaders of A and B to have a bargaining meeting to regulate against A’ (contrary to Carl’s narrative where leaders coordinate against loss of control). Subculture A’ comes to dominate discourse and cultural narratives in A, and makes A faster/​more productive than B, such as through the development of fully automated companies as in one of the Production Web stories. The resulting advantage of A is enough for A to begin dominating or at least threatening B geopolitically, but by that time leaders in A have little power to squash A’, so instead B follows suit by allowing a highly automation-oriented subculture B’s to develop. These advantages are small enough not to trigger regulatory oversight, but when integrated over time they are not “tiny”. This results in the gradual empowerment of humans who are misaligned with preserving human existence, until those humans also lose control of their own existence, perhaps willfully, or perhaps carelessly, or through a mix of both.

Here, the members of subculture A’ are misaligned with preserving the existence of humanity, but their tech is aligned with them.

• My best understanding of your position is: “Sure, but they will be trying really hard. So additional researchers working on the problem won’t much change their probability of success, and you should instead work on more-neglected problems.”

That is not my position if “you” in the story is “you, Paul Christiano” :) The closest position I have to that one is : “If another Paul comes along who cares about x-risk, they’ll have more positive impact by focusing on multi-agent and multi-stakeholder issues or ‘ethics’ with AI tech than if they focus on intent alignment, because multi-agent and multi-stakeholder dynamics will greatly affect what strategies AI stakeholders ‘want’ their AI systems to pursue.”

If they tried to get you to quit working on alignment, I’d say “No, the tech companies still need people working on alignment for them, and Paul is/​was one of those people. I don’t endorse converting existing alignment researchers to working on multi/​multi delegation theory (unless they’re naturally interested in it), but if a marginal AI-capabilities-bound researcher comes along, I endorse getting them set up to think about multi/​multi delegation more than alignment.”

• Carl, thanks for this clear statement of your beliefs. It sounds like you’re saying (among other things) that American and Chinese cultures will not engage in a “race-to-the-bottom” in terms of how much they displace human control over the AI technologies their companies develop. Is that right? If so, could you give me a % confidence on that position somehow? And if not, could you clarify?

To reciprocate: I currently assign a ≥10% chance of a race-to-the-bottom on AI control/​security/​safety between two or more cultures this century, i.e., I’d bid 10% to buy in a prediction market on this claim if it were settlable. In more detail, I assign a ≥10% chance to a scenario where two or more cultures each progressively diminish the degree of control they exercise over their tech, and the safety of the economic activities of that tech to human existence, until an involuntary human extinction event. (By comparison, I assign at most around a ~3% chance of a unipolar “world takeover” event, i.e., I’d sell at 3%.)

I should add that my numbers for both of those outcomes are down significantly from ~3 years ago due to cultural progress in CS/​AI (see this ACM blog post) allowing more discussion of (and hence preparation for) negative outcomes, and government pressures to regulate the tech industry.

• (I called the story an “outer” misalignment story because it focuses on the—somewhat improbable—case in which the intentions of the machines are all natural generalizations of their training objectives. I don’t have a precise definition of inner or outer alignment and think they are even less well defined than intent alignment in general, but sometimes the meaning seems unambiguous and it seemed worth flagging specifically because I consider that one of the least realistic parts of this story.)

Thanks; this was somewhat helpful to my understanding, because as I said,

> I currently can’t tell if by “outer alignment failure” you’re referring to the entire ecosystem of machines being outer-misaligned, or just each individual machine (and if so, which ones in particular), and I’d like to sync with your usage of the concept if possible (or at least know how to sync with it).

I realize you don’t have a precise meaning of outer misalignment in mind, but in my opinion, confusion around this concept is central to (in my opinion) confused expectation that “alignment solutions” are adequate (on the technological side) for averting AI x-risk.

My question: Are you up for making your thinking and/​or explaining about outer misalignment a bit more narratively precise here? E.g., could you say something like “«machine X» in the story is outer-misaligned because «reason»”?

Why I’m asking: My suspicion is that you answering this will help me pin down one of several possible substantive assumptions you and many other alignment-enthusiasts are making about the goals of AI designers operating in a multi-agent system or multi-polar singularity. Indeed, the definition of outer alignment currently endorsed by this forum is:

Outer Alignment in the context of machine learning is the property where the specified loss function is aligned with the intended goal of its designers. This is an intuitive notion, in part because human intentions are themselves not well-understood.

It’s conceivable to me that making future narratives much more specific regarding the intended goals of AI designers—and how they are or are not being violated—will either (a) clarify the problems I see with anticipating “alignment” solutions to be technically-adequate for existential safety, or (b) rescue the “alignment” concept with a clearer definition of outer alignment that makes sense in multi-agent systems.

So: thanks if you’ll consider my question!

• Paul, thanks writing this; it’s very much in line with the kind of future I’m most worried about.

For me, it would be super helpful if you could pepper throughout the story mentions of the term “outer alignment” indicating which events-in-particular you consider outer alignment failures. Is there any chance you could edit it to add in such mentions? E.g., I currently can’t tell if by “outer alignment failure” you’re referring to the entire ecosystem of machines being outer-misaligned, or just each individual machine (and if so, which ones in particular), and I’d like to sync with your usage of the concept if possible (or at least know how to sync with it).

• I don’t understand the claim that the scenarios presented here prove the need for some new kind of technical AI alignment research.

I don’t mean to say this post warrants a new kind of AI alignment research, and I don’t think I said that, but perhaps I’m missing some kind of subtext I’m inadvertently sending?

I would say this post warrants research on multi-agent RL and/​or AI social choice and/​or fairness and/​or transparency, none of which are “new kinds” of research (I promoted them heavily in my preceding post), and none of which I would call “alignment research” (though I’ll respect your decision to call all these topics “alignment” if you consider them that).

I would say, and I did say:

directing more x-risk-oriented AI research attention toward understanding RAAPs and how to make them safe to humanity seems prudent and perhaps necessary to ensure the existential safety of AI technology. Since researchers in multi-agent systems and multi-agent RL already think about RAAPs implicitly, these areas present a promising space for x-risk oriented AI researchers to begin thinking about and learning from.

I do hope that the RAAP concept can serve as a handle for noticing structure in multi-agent systems, but again I don’t consider this a “new kind of research”, only an important/​necessary/​neglected kind of research for the purposes of existential safety. Apologies if I seemed more revolutionary than intended. Perhaps it’s uncommon to take a strong position of the form “X is necessary/​important/​neglected for human survival” without also saying “X is a fundamentally new type of thinking that no one has done before”, but that is indeed my stance for X {a variety of non-alignment AI research areas}.

• > The objective of each company in the production web could loosely be described as “maximizing production″ within its industry sector.

Why does any company have this goal, or even roughly this goal, if they are aligned with their shareholders?

It seems to me you are using the word “alignment” as a boolean, whereas I’m using it to refer to either a scalar (“how aligned is the system?”) or a process (“the system has been aligned, i.e., has undergone a process of increasing its alignment”). I prefer the scalar/​process usage, because it seems to me that people who do alignment research (including yourself) are going to produce ways of increasing the “alignment scalar”, rather than ways of guaranteeing the “perfect alignment” boolean. (I sometimes use “misaligned” as a boolean due to it being easier for people to agree on what is “misaligned” than what is “aligned”.) In general, I think it’s very unsafe to pretend numbers that are very close to 1 are exactly 1, because e.g., 1^(10^6) = 1 whereas 0.9999^(10^6) very much isn’t 1, and the way you use the word “aligned” seems unsafe to me in this way.

(Perhaps you believe in some kind of basin of convergence around perfect alignment that causes sufficiently-well-aligned systems to converge on perfect alignment, in which case it might make sense to use “aligned” to mean “inside the convergence basin of perfect alignment”. However, I’m both dubious of the width of that basin, and dubious that its definition is adequately social-context-independent [e.g., independent of the bargaining stances of other stakeholders], so I’m back to not really believing in a useful Boolean notion of alignment, only scalar alignment.)

In any case, I agree profit maximization it not a perfectly aligned goal for a company, however, it is a myopically pursued goal in a tragedy of the commons resulting from a failure to agree (as you point out) on something better to do (e.g., reducing competitive pressures to maximize profits).

I guess this is probably just a gloss you are putting on the combined behavior of multiple systems, but you kind of take it for given rather than highlighting it as a serious bargaining failure amongst the machines, and more importantly you don’t really say how or why this would happen.

I agree that it is a bargaining failure if everyone ends up participating in a system that everyone thinks is bad; I thought that would be an obvious reading of the stories, but apparently it wasn’t! Sorry about that. I meant to indicate this with the pointers to Dafoe’s work on “Cooperative AI” and Scott Alexander’s “Moloch” concept, but looking back it would have been a lot clearer for me to just write “bargaining failure” or “bargaining non-starter” at more points in the story.

The implicit argument seems to apply just as well to humans trading with each other and I’m not sure why the story is different if we replace the humans with aligned AI. [...] Maybe you think we are already losing sight of our basic goals and collectively pursuing alien goals

Yes, you understand me here. I’m not (yet?) in the camp that we humans have “mostly” lost sight of our basic goals, but I do feel we are on a slippery slope in that regard. Certainly many people feel “used” by employers/​ institutions in ways that are disconnected with their values. People with more job options feel less this way, because they choose jobs that don’t feel like that, but I think we are a minority in having that choice.

> However, their true objectives are actually large and opaque networks of parameters that were tuned and trained to yield productive business practices during the early days of the management assistant software boom.

This sounds like directly saying that firms are misaligned.

I would have said “imperfectly aligned”, but I’m happy to conform to “misaligned” for this.

I agree that competitive pressures to produce imply that firms do a lot of producing and saving, just as it implies that humans do a lot of producing and saving.

Good, it seems we are synced on that.

And in the limit you can basically predict what all the machines do, namely maximally efficient investment.

Yes, it seems we are synced on this as well. Personally, I find this limit to be a major departure from human values, and in particular, it is not consistent with human existence.

But that doesn’t say anything about what the society does with the ultimate proceeds from that investment.

The attractor I’m pointing at with the Production Web is that entities with no plan for what to do with resources—other than “acquire more resources”—have a tendency to win out competitively over entities with non-instrumental terminal values like “humans having good relationships with their children”. I agree it will be a collective bargaining failure on the part of humanity if we fail to stop our own replacement by “maximally efficient investment” machines with no plans for what to do with their investments other than more investment. I think the difference between mine and your views here is that I think we are on track to collectively fail in that bargaining problem absent significant and novel progress on “AI bargaining” (which involves a lot of fairness/​transparency) and the like, whereas I guess you think we are on track to succeed?

You might say: investment has to converge to 100% since people with lower levels of investment get outcompeted.

Yep!

But this it seems like the actual efficiency loss required to preserve human values seems very small even over cosmological time (e.g. see Carl on exactly this question).

I agree, but I don’t think this means we are on track to keeping the humans, and if we are on track in my opinion it will be mostly-because of (say, using Shapley value to define “mostly because of”) of technical progress on bargaining/​cooperation/​governance solutions rather than alignment solutions.

And more pragmatically, such competition most obviously causes harm either via a space race and insecure property rights,

I agree; competition causing harm is key to my vision of how things will go, so this doesn’t read to me as a counterpoint; I’m not sure if it was intended as one though?

or war between blocs with higher and lower savings rates

+1 to this as a concern; I didn’t realize other people were thinking about this, so good to know.

(some of them too low to support human life, which even if you don’t buy Carl’s argument is really still quite low, conferring a tiny advantage)

I think I disagree with you on the tininess of the advantage conferred by ignoring human values early on during a multi-polar take-off. I agree the long-run cost of supporting humans is tiny, but I’m trying to highlight a dynamic where fairly myopic/​nihilistic power-maximizing entities end up quickly out-competing entities with other values, due to, as you say, bargaining failure on the part of the creators of the power-maximizing entities.

Why wouldn’t an aligned CEO sit down with the board to discuss the situation openly with them?

In the failure scenario as I envision it, the board will have already granted permission to the automated CEO to act much more quickly in order to remain competitive, such that the AutoCEO isn’t checking in with the Board enough to have these conversations. The AutoCEO is highly aligned with the Board in that it is following their instruction to go much faster, but in doing so it makes a larger number of tradeoff that the Board wishes they didn’t have to make. The pressure to do this results from a bargaining failure between the Board and other Boards who are doing the same thing and wishing everyone would slow down and do things more carefully and with more coordination/​bargaining/​agreement.

Can you explain the decisions an individual aligned CEO makes as its company stops benefiting humanity? I can think of a few options:

• Actually the CEOs aren’t aligned at this point. They were aligned but then aligned CEOs ultimately delegated to unaligned CEOs. But then I agree with Vanessa’s comment.

• The CEOs want to benefit humanity but if they do things that benefit humanity they will be outcompeted. so they need to mostly invest in remaining competitive, and accept smaller and smaller benefits to humanity. But in that case can you describe what tradeoff concretely they are making, and in particular why they can’t continue to take more or less the same actions to accumulate resources while remaining responsive to shareholder desires about how to use those resources?

Yes, it seems this is a good thing to hone in on. As I envision the scenario, the automated CEO is highly aligned to the point of keeping the Board locally happy with its decisions conditional on the competitive environment, but not perfectly aligned, and not automatically successful at bargaining with other companies as a result of its high alignment. (I’m not sure whether to say “aligned” or “misaligned” in your boolean-alignment-parlance.) At first the auto-CEO and the Board are having “alignment check-ins” where the auto-CEO meets with the Board and they give it input to keep it (even) more aligned than it would be without the check-ins. But eventually the Board realizes this “slow and bureaucratic check-in process” is making their company sluggish and uncompetitive, so they instruct the auto-CEO more and more to act without alignment check ins. The auto-CEO might warns them that this will decrease its overall level of per-decision alignment with them, but they say “Do it anyway; done is better than perfect” or something along those lines. All Boards wish other Boards would stop doing this, but neither they nor their CEOs manage to strike up a bargain with the rest of the world stop it. This concession by the Board—a result of failed or non-existent bargaining with other Boards [see: antitrust law]—makes the whole company less aligned with human values.

The win scenario is, of course, a bargain to stop that! Which is why I think research and discourse regarding how the bargaining will work is very high value on the margin. In other words, my position is that the best way for a marginal deep-thinking researcher to reduce the risks of these tradeoffs is not to add another brain to the task of making it easier/​cheaper/​faster to do alignment (which I admit would make the trade-off less tempting for the companies), but to add such a researcher to the problem of solving the bargaining/​cooperation/​mutual-governance problem that AI-enhanced companies (and/​or countries) will be facing.

If trillion-dollar tech companies stop trying to make their systems do what they want, I will update that marginal deep-thinking researchers should allocate themselves to making alignment (the scalar!) cheaper/​easier/​better instead of making bargaining/​cooperation/​mutual-governance cheaper/​easier/​better. I just don’t see that happening given the structure of today’s global economy and tech industry.

Somehow the machine interests (e.g. building new factories, supplying electricity, etc.) are still being served. If the individual machines are aligned, and food/​oxygen/​etc. are in desperately short supply, then you might think an aligned AI would put the same effort into securing resources critical to human survival. Can you explain concretely what it looks like when that fails?

Yes, thanks for the question. I’m going to read your usage of “aligned” to mean “perfectly-or-extremely-well aligned with humans”. In my model, by this point in the story, there has a been a gradual decrease in the scalar level of alignment of the machines with human values, due to bargaining successes on simpler objectives (e.g., «maximizing production») and bargaining failures on more complex objectives (e.g., «safeguarding human values») or objectives that trade off against production (e.g., «ensuring humans exist»). Each individual principal (e.g., Board of Directors) endorsed the gradual slipping-away of alignment-scalar (or failure to improve alignment-scalar), but wished everyone else would stop allowing the slippage.

• These management assistants, DAOs etc are not aligned to the goals of their respective, individual users/​owners.

How are you inferring this? From the fact that a negative outcome eventually obtained? Or from particular misaligned decisions each system made? It would be helpful if you could point to a particular single-agent decision in one of the stories that you view as evidence of that single agent being highly misaligned with its user or creator. I can then reply with how I envision that decision being made even with high single-agent alignment.

1. Maybe several AI systems aligned to different users with different interests can interact in a Pareto inefficient way (a tragedy of the commons among the AIs), and maybe this can be prevented by designing the AIs in particular ways.

Yes, this^.

• I hadn’t read it (nor almost any science fiction books/​stories) but yes, you’re right! I’ve now added a callback to Autofac after the “facotiral DAO” story. Thanks.

• Good to hear!

If I read that term [“AI existential safety”] without a definition I would assume it meant “reducing the existential risk posed by AI.” Hopefully you’d be OK with that reading. I’m not sure if you are trying to subtly distinguish it from Nick’s definition of existential risk or if the definition you give is just intended to be somewhere in that space of what people mean when they say “existential risk” (e.g. the LW definition is like yours).

Yep, that’s my intention. If given the chance I’d also shift the meaning of “existential risk” a bit away from Bostrom’s and a bit toward a more naive meaning of the term, but that’s a separate objective :) Specifically, if I got to rewrite Nick’s terminology (which might be too late now that it’s on Wikipedia), I’d say “existential risk” should mean “risk to the existence of humanity” and “existential-level risk” should mean “risks that are as morally significant as risks to the existence of humanity” (which, roughly speaking, is what Bostrom currently calls “existential risk”).