Anticipating the argument that, since we’re doing the training, we can shape the goals of the systems—this would certainly be reason for optimism if we had any idea what goals we would see emerge while training superintelligent systems, and had any way of actively steering those goals to our preferred ends. We don’t have either, right now.
What does this even mean? I’m pretty skeptical of the realist attitude toward “goals” that seems to be presupposed in this statement. Goals are just somewhat useful fictions for predicting a system’s behavior in some domains. But I think it’s a leaky abstraction that will lead you astray if you take it too seriously / apply it out of the domain in which it was designed for.
We clearly can steer AI’s behavior really well in the training environment. The question is just whether this generalizes. So it becomes a question of deep learning generalization. I think our current evidence from LLMs strongly suggests they’ll generalize pretty well to unseen domains. And as I said in the essay I don’t think the whole jailbreaking thing is any evidence for pessimism— it’s exactly what you’d expect of aligned human mind uploads in the same situation.
The positive case is just super obvious, it’s that we’re trying very hard to make these systems aligned, and almost all the data we’re dumping into these systems is generated by humans and is therefore dripping with human values and concepts.
I also think we have strong evidence from ML research that ANN generalization is due to symmetries in the parameter-function map which seem generic enough that they would apply mutatis mutandis to human brains, which also have a singular parameter-function map (see e.g. here).
I do in fact think that evidence from evolution suggests that values are strongly contingent on the kinds of selection pressures which produced various species.
Not really sure what you’re getting at here/why this is supposed to help your side
I’m not conditioning on the global governance mechanism— I assign nonzero probability mass to the “standard treaty” thing— but I think in fact you would very likely need global governance, so that is the main causal mechanism through which tyranny happens in my model
And you’ve already agreed that it’s implausible that these efforts would lead to tyranny, you think they will just fail.
I think that conditional on the efforts working, the chance of tyranny is quite high (ballpark 30-40%). I don’t think they’ll work, but if they do, it seems quite bad.
And since I think x-risk from technical AI alignment failure is in the 1-2% range, the risk of tyranny is the dominant effect of “actually enforced global AI pause” in my EV calculation, followed by the extra fast takeoff risks, and then followed by “maybe we get net positive alignment research.”
I have now made a clarification at the very top of the post to make it 1000% clear that my opposition is disjunctive, because people repeatedly get confused / misunderstand me on this point.
Please stop saying that mind-space is an “enormously broad space.” What does that even mean? How have you established a measure on mind-space that isn’t totally arbitrary?
What if concepts and values are convergent when trained on similar data, just like we see convergent evolution in biology?
I think this post is best combined with my post. Together, these posts present a coherent, disjunctive set of arguments against pause.
My opposition is disjunctive!
I both think that if it’s possible to stop the building of dangerously large models via international regulation, that would be bad because of tyranny risk, and I also think that we very likely can’t use international regulation to stop building these things, so that any local pauses are not going to have their intended effects and will have a lot of unintended net-negative effects.
(Also, reread my piece—I call for action to regulate and stop larger and more dangerous models immediately as a prelude to a global moratorium. I didn’t say “wait a while, then impose a pause for a while in a few places.”)
This really sounds like you are committing the fallacy I was worried about earlier on. I just don’t agree that you will actually get the global moratorium. I am fully aware of what your position is.
In my essay I don’t make an assumption that the pause would immediate, because I did read your essay and I saw that you were proposing that we’d need some time to prepare and get multiple countries on board.
I don’t see how a delay before a pause changes anything. I still think it’s highly unlikely you’re going to get sufficient international backing for the pause, so you will either end up doing a pause with an insufficiently large coalition, or you’ll back down and do no pause at all.
Differentiability is a pretty big part of the white box argument.
The terabyte compiled executable binary is still white box in a minimal sense but it’s going to take a lot of work to mould that thing into something that does what you want. You’ll have to decompile it and do a lot of static analysis, and Rice’s theorem gets in the way of the kinds of stuff you can prove about it. The code might be adversarially obfuscated, although literal black box obfuscation is provably impossible.
If instead of a terabyte of compiled code, you give me a trillion neural net weights, I can fine tune that network to do a lot of stuff. And if I’m worried about the base model being preserved underneath and doing nefarious things, I can generate synthetic data from the fine tuned model and train a fresh network from scratch on that (although to be fair that’s pretty compute-intensive).
It’s not obvious to me what alignment optimism has to do with the pause debate
Sorry, I thought it would be fairly obvious how it’s related. If you’re optimistic about alignment then the expected benefits you might hope to get out of a pause (whether or not you actually do get those benefits) are commensurately smaller, so the unintended consequences should have more relative weight in your EV calculation.
To be clear, I think slowing down AI in general, as opposed to the moratorium proposal in particular, is a more reasonable position that’s a bit harder to argue against. I do still think the overhang concerns apply in non-pause slowdowns but in a less acute manner.
It’s essentially no cost to run a gradient-based optimizer on a neural network, and I think this is sufficient for good-enough alignment. I view the the interpretability work I do at Eleuther as icing on the cake, allowing us to steer models even more effectively than we already can. Yes, it’s not zero cost, but it’s dramatically lower cost than it would be if we had to crack open a skull and do neurosurgery.
Also, if by “mechanistic interpretability” you mean “circuits” I’m honestly pretty pessimistic about the usefulness of that kind of research, and I think the really-useful stuff is lower cost than circuits-based interp.
That if there was a pause, alignment research would magically revert back to what it was back in the MIRI days
The claim is more like, “the MIRI days are a cautionary tale about what may happen when alignment research isn’t embedded inside a feedback loop with capabilities.” I don’t literally believe we would revert back to pure theoretical research during a pause, but I do think the research would get considerably lower quality.
However, I’m worried that your [white box] framing is confusing and will cause people to talk past each other.
Perhaps, but I think the current conventional wisdom that neural nets are “black box” is itself a confusing and bad framing and I’m trying to displace it.
Yep I am aware of the value learning section of Chapter 12, which is why I used the “mostly” qualifier. That said he basically imagines something like Stuart Russell’s CIRL, rather than anything like LLMs or imitation learning.
If we treat the Orthogonality Thesis as the crux of the book, I also think the book has aged poorly. In fact it should have been obvious when the book was written that the Thesis is basically a motte-and-bailey where you argue for a super weak claim (any combo of intelligence and goals is logically possible), which is itself dubious IMO but easy to defend, and then pretend like you’ve proven something much stronger, like “intelligence and goals will be empirically uncorrelated in the systems we actually build” or something.
Yep it’s all meant to be disjunctive and yep it could have been clearer. FWIW this essay went through multiple major revisions and at one point I was trying to make the disjunctivity of it super clear but then that got de-prioritized relative to other stuff. In the future if/when I write about this I think I’ll be able to organize things significantly better
You need to have some motivation for thinking that a fundamentally new kind of danger will emerge in future systems, in such a way that we won’t be able to handle it as it arises. Otherwise anyone can come up with any nonsense they like.
If you’re talking about e.g. Evan Hubinger’s arguments for deceptive alignment, I think those arguments are very bad, in light of 1) the white box argument I give in this post, 2) the incoherence of Evan’s notion of “mechanistic optimization,” and 3) his reliance on “counting arguments” where you’re supposed to assume that the “inner goals” of the AI are sampled “uniformly at random” from some uninformative prior over goals (I don’t think the LLM / deep learning prior is uninformative in this sense at all).
the “pause” would be a temporary measure imposed by some countries, as opposed to a stop-gap solution and regulation imposed to enable stronger international regulation, which Nora says she supports
I don’t understand the distinction you’re trying to make between these two things. They really seem like the same thing to me, because a stop-gap measure is temporary by definition:
I’m also against a global pause even if we can make it happen, and I say so in the post:
If in spite of all this, we somehow manage to establish a global AI moratorium, I think we should be quite worried that the global government needed to enforce such a ban would greatly increase the risk of permanent tyranny, itself an existential catastrophe. I don’t have time to discuss the issue here, but I recommend reading Matthew Barnett’s “The possibility of an indefinite AI pause” and Quintin Pope’s “AI is centralizing by default; let’s not make it worse,” both submissions to this debate.
Why does it have to be one or the other? I personally don’t put much stock in what Eliezer and Nate think, but many other people do.
Where we agree:
“dangerous-capability-model-eval-based regulation” sounds good to me. I’m also in favor of Robin Hanson’s foom liability proposal. These seem like very targeted measures that would plausibly reduce the tail risk of existential catastrophe, and don’t have many negative side effects. I’m also not opposed to the US trying to slow down other states, although it’d depend on the specifics of the proposal.
Where we (partially) disagree:
I think there’s a plausible case to be made that publishing model weights reduces foom risk by making AI capabilities more broadly distributed, and also enhances security-by-transparency. Of course there are concerns about misuse— I do think that’s a real thing to be worried about— but I also think it’s generally exaggerated. I also relatively strongly favor open source on purely normative grounds. So my inclination is to be in favor of it but with reservations. Same goes for labs publishing capabilities research.
I don’t think the terminal vs. instrumental goal dichotomy is very helpful, because it shifts the focus away from behavioral stuff we can actually measure (at least in principle). I also don’t think humans exhibit this distinction particularly strongly. I would prefer to talk about generalization, which is much more empirically testable and has a practical meaning.