FWIW, I don't think (1) or (2) plays a role in why MIRI researchers work on the research they do, and I don't think they play a role in why people at MIRI think "learning to reason from humans" isn't likely to be sufficient. The shape of the "HRAD is more promising than act-based agents" claim is more like what Paul Christiano said here:

As far as I can tell, the MIRI view is that my work is aimed at [a] problem which is not possible, not that it is aimed at a problem which is too easy. [...] One part of this is the disagreement about whether the overall approach I'm taking could possibly work, with my position being "something like 50-50" the MIRI position being "obviously not" [...]

There is a broader disagreement about whether any "easy" approach can work, with my position being "you should try the easy approaches extensively before trying to rally the community behind a crazy hard approach" and the MIRI position apparently being something like "we have basically ruled out the easy approaches, but the argument/evidence is really complicated and subtle."

With a clarification I made in the same thread:

I think Paul's characterization is right, except I think Nate wouldn't say "we've ruled out all the prima facie easy approaches," but rather something like "part of the disagreement here is about which approaches are prima facie 'easy.'" I think his model says that the proposed alternatives to MIRI's research directions by and large look more difficult than what MIRI's trying to do, from a naive traditional CS/Econ standpoint. E.g., I expect the average game theorist would find a utility/objective/reward-centered framework much less weird than a recursive intelligence bootstrapping framework. There are then subtle arguments for why intelligence bootstrapping might turn out to be easy, which Nate and co. are skeptical of, but hashing out the full chain of reasoning for why a daring unconventional approach just might turn out to work anyway requires some complicated extra dialoguing. Part of how this is framed depends on what problem categories get the first-pass "this looks really tricky to pull off" label.

Did anything in Nate's post or my comments strike you as "pushing for a singleton"? When people say "singleton," I usually understand them to have in mind some kind of world takeover, which sounds like what you're talking about here. The strategy people at MIRI favor tends to be more like "figure out what minimal AI system can end the acute risk period (in particular, from singletons), while doing as little else as possible; then steer toward that kind of system". This shouldn't be via world takeover if there's any less-ambitious path to that outcome, because any added capability, or any added wrinkle in the goal you're using the system for, increases accident risk.

More generally, alignment is something that you can partially solve for systems with some particular set of capabilities, rather than being all-or-nothing.

I agree entirely that we don't know this yet - whether for rabbits or for future AIs - that's part of what I'd need to understand before I'd agree that a singleton seems like our best chance at a good future.

I think it's much less likely that we can learn that kind of generalization in advance than that we can solve most of the alignment problem in advance. Additionally, solving this doesn't in any obvious way get you any closer to being able to block singletons from being developed, in the scenario where singletons are "possible but only with some effort made". Knowing about the utility of a multipolar outcome where no one ever builds a singleton can be useful for knowing whether you should aim for a multipolar outcome where no one ever build a singleton, but it doesn't get us any closer to knowing how to prevent anyone from ever building a singleton if you find a way to achieve an initially multipolar outcome.

I'd also add that I think the risk of producing bad conscious states via non-aligned AI mainly lies in AI systems potentially having parts or subsystems that are conscious, rather than in the system as a whole (or executive components) being conscious in the fashion of a human.

You're right that we can't be sure that conscious beings will do good things, but we don't have that assurance for any outcome we might push for.

One way to think about the goal is that we want to "zero in" on valuable futures: it's unclear what exactly a good future looks like, and we can't get an "assurance," but for example a massive Manhattan Project to develop whole brain emulation is a not-implausible path to zeroing in, assuming WBE isn't too difficult to achieve on the relevant timescale and assuming you can avoid accelerating difficult-to-align AI too much in the process. It's a potentially promising option for zeroing in because emulated humans could be leveraged to do a lot of cognitive work in a compressed period of time to sort out key questions in moral psychology+philosophy, neuroscience, computer science, etc. that we need to answer in order to get a better picture of good outcomes.

This is also true for a Manhattan Project to develop a powerful search algorithm that generates smart creative policies to satisfy our values, while excluding hazardous parts of the search space -- this is the AI route.

Trying to ensure that AI is conscious, without also solving WBE or alignment or global coordination or something of that kind in the process, doesn't have this "zeroing in" property. It's more of a gamble that hopefully good-ish futures have a high enough base rate even when we don't put a lot of work into steering in a specific direction, that maybe arbitrary conscious systems would make good things happen. But building a future of conscious AI systems opens up a lot of ways for suffering to end up proliferating in the universe, just as it opens up a lot of ways for happiness to end up proliferating in the universe. Just as it isn't obvious that e.g. rabbits experience more joy than suffering in the natural world, it isn't obvious that conscious AI systems in a multipolar outcome would experience more joy than suffering. (Or otherwise experience good-on-net lives.)

True, but if a singleton isn't inevitable, trying to create one will itself pose a serious existential risk, as would any similar world takeover attempt.

I think if an AI singleton isn't infeasible or prohibitively difficult to achieve, then it's likely to happen eventually regardless of what we'd ideally prefer to have happen, absent some intervention to prevent it. Either it's not achievable, or something needs to occur to prevent anyone in the world from reaching that point. If you're worried about singletons, I don't think pursuing multipolar outcomes and/or conscious-AI outcomes should be a priority for you, because I don't think either of those paths concentrates very much probability mass (if any) into scenarios where singletons start off feasible but something blocks them from occurring.

Multipolar scenarios are likelier to occur in scenarios where singletons simply aren't feasible, as a background fact about the universe; but conditional on singletons being feasible, I'm skeptical that achieving a multipolar AI outcome would do much (if anything) to prevent a singleton from occurring afterward, and I think it would make alignment much more difficult.

Alignment and WBE look like difficult tasks, but they have the "zeroing in" property, and we don't know exactly how difficult they are. Alignment in particular could turn out to be much harder than it looks or much easier, because there's so little understanding of what specifically is required. (Investigating WBE has less value-of-information because we already have some decent WBE roadmaps.)

Consciousness is something people at MIRI have thought about quite a bit, and we don't think people should ignore the issue. But it's a conceptually separate issue from intelligence, and it's important to be clear about that.

One reason to prioritize the AI alignment issue over consciousness research is that a sufficiently general solution to AI alignment would hopefully also resolve the consciousness problem: we care about the suffering, happiness, etc. of minds in general, so if we successfully build a system that shares and promotes our values, that system would hopefully also look out for the welfare of conscious machines, if any exist. That includes looking out for its own welfare, if it's conscious.

In contrast, a solution to the consciousness problem doesn't get us a solution to the alignment problem, because there's no assurance that conscious beings will do things that are good (including good for the welfare of conscious machines).

Some consciousness-related issues are subsumed in alignment, though. E.g., a plausible desideratum for early general AI systems is "limit its ability to model minds" ('behaviorist' AI). And we do want to drive down the probability that the system is conscious if we can find a way to do that.

Could you or Will provide an example of a source that explicitly uses "GCR" and "xrisk" in such a way that there are non-GCR xrisks? You say this is the most common operationalization, but I'm only finding examples that treat xrisk as a subset of GCR, as the Bostrom quote above does.

And it's framed as long-run future because we think that there are potentially lots of things that could have a huge positive on the value of the long-run future which aren't GCRs - like humanity having the right values, for example.

I don't have much to add to what Rob W and Carl said, but I'll note that Bostrom defined "existential risk" like this back in 2008:

A subset of global catastrophic risks is existential risks. An existential risk is one that threatens to cause the extinction of Earth-originating intelligent life or to reduce its quality of life (compared to what would otherwise have been possible) permanently and drastically.

Presumably we should replace "intelligent" here with "sentient" or similar. The reason I'm quoting this is that on the above definition, it sounds like any potential future event or process that would cost us a large portion of the future's value counts as an xrisk (and therefore as a GCR). 'Humanity's moral progress stagnates or we otherwise end up with the wrong values' sounds like a global catastrophic risk to me, on that definition. (From a perspective that does care about long-term issues, at least.)

I'll note that I think there's at least some disagreement at FHI / Open Phil / etc. about how best to define terms like "GCR", and I don't know if there's currently a consensus or what that consensus is. Also worth noting that the "risk" part is more clearly relevant than the "global catastrophe" part -- malaria and factory farming are arguably global catastrophes in Bostrom's sense, but they aren't "risks" in the relevant sense, because they're already occurring.

The discussion of CFAR's pivot to focusing on existential risk seemed to use "cause-neutral" to mean something like "cause-general".

Confusingly, the way "cause-neutral" was used there directly contradicts its use here: there, it meant avoiding cause-impartially favoring a specific cause based on its apparent expected value, in favor of a cause-partial commitment to pet causes like rationality and EA capacity-building. (Admittedly, at the organizational level it often makes sense to codify some "pet causes" even if in principle the individuals in that organization are trying to maximize global welfare impartially.)

... Aaand 33 hours later: https://twitter.com/mpshanahan/status/836249423369756672