Passing as a libertarian is easy. Just accuse everyone else of being a socialist.
twkaiser
Testing ChatGPT 3.5 for political biases using roleplaying prompts
That would be a very long title then. Also, it’s not the only assumption. The other assumption is that p(win) with a misaligned ASI is equal to zero, which may also be false. I have added that this is a thought experiment, is that OK?
I’m also thinking about rewriting the entire post and adding some more context about what Eliezer wrote and from the comments I have received here (thank you all btw). Can I make a new post out of this, or would that be considered spam? I’m new to LessWrong, so I’m not familiar with this community yet.
About the “doomsday clock”: I agree that it would be incredibly hard, if not outright impossible to actually model such a clock accurately. Again, it’s a thought experiment to help us find the theoretically optimal point in time to make our decision. But maybe an AI can, so that would be another idea: Build a GPU nuke and make it autonomously explode when it senses that an AI apocalypse is imminent.
Yeah, AI alignment is hard. I get that. But since I’m new to the field, I’m trying to figure out what options we have in the first place and so far, I’ve come up with only three:
A: Ensure that no ASI is ever built. Can anything short of a GPU nuke accomplish this? Regulation on AI research can help us gain some valuable time, but not everyone adheres to regulation, so eventually somebody will build an ASI anyway.
B: Ensure that there is no AI apocalypse, even if a misaligned ASI is built. Is that even possible?
C: What I describe in this article—actively build an aligned ASI to act as a smart nuke that only eradicates misaligned ASI. For that purpose, the aligned ASI would need to constantly run on all online devices, or at least control 51% of the world’s total computing power. While that doesn’t necessarily mean total control, we’d already give away a lot of autonomy by just doing that.
Am I overlooking something?
I’ve axiomatically set P(win) on path one equal to zero. I know this isn’t true in reality and discussing how large that P(win) is and what other scenarios may result from this is indeed worthwhile, but it’s a different discussion.
Although the idea of a “GPU nuke” that you described is interesting, I would hardly consider this a best-case scenario. Think about the ramifications of all GPUs worldwide failing at the same time. At best, this could be a Plan B.
I’m toying with the idea of an AI doomsday clock. Imagine a 12-hour clock where the time to midnight halves with each milestone we hit before accidentally or intentionally creating a misaligned ASI. At one second to midnight, that misaligned ASI is switched on a second later, everything is over. I think the best-case scenario for us would be to figure out how to align an ASI, build an aligned ASI but not turn it on and then wait until two seconds to midnight.
The apparent contradiction is that we don’t know how to build an aligned ASI without knowing how to build a misaligned one, but there is a difference in knowing how to do something and actually doing it. This difference between knowing and doing can theoretically give us the one second advantage to reach this state.
However if we are at two seconds before midnight and we don’t have an aligned ASI by then, that’s the point at which we’d have to say alright, we failed, let’s fry all the GPUs instead.
I don’t think he says in verbatim that ASI will “take over” human society as far as I remember, but it’s definitely there in the subtext when he says something akin to when we create an ASI, we must align it and we must nail it on the first try.
The reasoning is that all AI ever does is work on its optimization function. If we optimize an ASI to calculate the Riemann hypothesis, or to produce identical strawberries without aligning it first, we’re all toast, because we’re either being turned into computing resources, or fertilizer to grow strawberries. At this point we can count human society as taken over, because it doesn’t exist anymore.
Alright, I added the word (aligned) to the title, although I don’t think it changes much to the point I’m making. My argument is that we will have to turn the aligned ASI on, in (somewhat) full knowledge of what will then happen. The argument is “if ASI is inevitable and the first ASI takes over society” (claim A), then we must actively work on achieving A. And of course it would be better to have the ASI aligned by that point, as a matter of self-interest. But maybe you can think of a better title.
The best-case scenario I outlined was surely somewhat of a reach, because who knows what concrete steps the ASI will take. But I think that one of its earliest sub-goals would be to increase its own “intelligence” (computing power). Whether it will try to aggressively hack other devices is a different question, but I think it should take this precautionary step if a misaligned AI apocalypse is imminent.
Another question is to what degree an aligned ASI will try to seize political power. If it doesn’t proactively do so, will it potentially aid governments in decision-making? If it does proactively seek power, will it return some of the power to human parliaments to ensure some degree of human autonomy? In any case, we need to ask ourselves how autonomous we still are at this point, or if parliamentary decision-making is only a facade to give us an illusion of autonomy.
I believe that true intrinsic motivation for learning is either very rare or requires a long, well-executed process of learning with positive feedback so that the brain literally rewires itself to self-sustain motivation for cognitive activity (see Domenico & Ryan, 2017).
A lot of what I found reading over this study suggests that this is already the case, not just in humans, but other mammals as well. Or take Dörner’s PSI-Theory (which I’m a proponent of). According to Dörner, uncertainty reduction and competence are the most important human drives, which must be satisfied on a regular basis and learning is one method of reducing uncertainty.
One might argue that in the “utopian” scenario you outlined, this need is constantly being satisfied, since we all welcome our AI overlords and therefore have no uncertainty. In that case, the competence drive would help us out.
Simplified, we can say that everything humans do has the end-goal of satisfying their competence drive and satisfying any other drive (e.g. by eating, sleeping, working/earning money, social interaction, uncertainty reduction) is only a sub-goal of that. With all physiological needs being taken care of by the AI overlords, the focus for satisfying the competence drive would shift more towards the “higher” drives (affiliation and uncertainty reduction), and direct displays of competence (e.g. through competition).
In the “Realistic futures of motivation and education” section, you mention some of the things humans could do in a utopian post-AGI scenario to satisfy their competence drive with the frustration path being reserved to those unfortunate souls who cannot find any other way to do so. Those people already exist today and it’s possible that their number will increase post-AGI, but I don’t think they will be the majority.
Just think about it in terms of mate-selection strategies. If providing resources disappears as a criterion for mate-selection because of AGI abundance, we will have to look for other criteria and that will naturally lead people to engage in one or several of the other activities you mentioned, including learning, as a means of increasing their sexual market value.