Slow motion videos as AI risk intuition pumps

10 million times faster is really a lot - on modern hardware, running SOTA object segmentation models at even 60fps is quite hard, and those are usually much much smaller than the kinds of AIs we would think about in the context of AI risk.

But - 100x faster is totally plausible (especially w/100x the energy consumption!) - and I think the argument still mostly works at that much more conservative speedup.

In the same vein, I humbly suggest "The entire bee movie but every time they say bee it gets faster" as a good model for what the singularity will seem like from our perspective.

This does seem like a helpful intuition pump.

Curious how many people you've tried this with, and what sort of specific responses they tend to have.

Cool idea. By default I might suggest this video instead - very similar to yours, but with a girl running down the track, so you can actually see how slowed down it is (as opposed to it looking like a still frame).

This may be persuasive, but does it pump intuitions in the direction of an accurate assessment of AGI risk? While you never explicitly state that this is your goal, I think it's safe to assume given that you're posting on LW.

As Nikita Sokolsky argued here [LW · GW], it's not clear that a 10-million fold difference in processing speed leads to a 10-million fold difference in capabilities. Even a superintelligent AI may be restricted to manipulating the world via physical processes and mechanisms that take human-scale time to execute. To establish a unique danger from AGI, it seems important to identify concrete attack vectors that are available to an AGI, but not to humans, due to the processing speed differential.

While it may be that a person hearing this "slow-motion camera" argument can conceive of this objection on their own, I think the point of an intuition pump is to persuade somebody who's unlikely to think of it independently. For this reason, I think that identifying at least one concrete AGI-tractable, human-intractable attack vector would be a more useful and accuracy-promoting intuition pump than the "slow-motion camera" pump.

Fortunately, articulating those AGI-unique attack vectors in public is not a particularly unsafe practice. Attack ideas generated by deliberately trying to find ideas that are impossible for humans, but tractable for AGI are unlikely to be preferable to a bad actor to an attack generated by trying to think of easy ways for a human to cause harm.

I think this is one place where reading science fiction improves people's judgment. Without reading so many monologues and descriptions of AI making decisions in milliseconds, I'd probably not be able to bring this to mind as plausible nearly as easily.

Now, when you try imagining things turning out fine for humanity over the course of a year, try imagining advanced AI technology running all over the world and making all kinds of decisions and actions 10 million times faster than us, for 10 million subjective years. [emphasis and de-emphasis mine]

Would actions also be 10 million times faster? I'm too tired to do the math, but I think actuators tend to have a characteristic time-scale below which they're hard to control. Similarly, the speed of light limits how quickly you can communicate stuff to different places on earth.

What is the source on this being slowed down by 100x? 

Here it says Magyar filmed at 1300 fps, and the video info says 50 fps; does this imply 1300/50=26x slow down? 

Also, if the video is 120 seconds long, 100x slow down implies the train stopping took 1.2 seconds, which seems too fast. 

26x slow down implies the train took 4.6 seconds to stop, which seems more plausible to me.  

Points from this post I agree with:

• AGI will have at least 100x faster decision making speed for any given decision, compared to human decision making
• AGI will be able to interact with all 9 billion humans at once, in parallel, giving it a massive advantage
• Slow motion videos present a helpful analogy

My objection is primarily around the fact that having a 100x faster processing power wouldn't automatically allow you to do things 100x faster in the physical world:

1. Any mechanical systems that you control won't be 100x faster due to limitations of how faster real-world mechanical parts will work. I.e. if you control a drone, you have to deal with the fact that the drone won't fly/rotate 100x faster just because your processing power is 100x faster. And you'll probably have to control the drone remotely because you wouldn't fit the entire AGI on the drone itself, placing a limit on how fast you can make decisions.
2. Any operations where you rely on human action will run at 1x speed, even if you somewhat streamline them thanks to parallelization and superior decision making
3. Being 100x faster is useless if you don't have full information on what the humans are doing/plotting. And they could hide pretty easily by meeting up offline with no electronics in place.

Recently I've had success introducing people to AI risk by telling them about ELK, and specifically how human simulation is likely to be favored. Providing this or a similarly general argument, e.g. that power-seeking is convergent, seems both more intuitive (humans can also do simulation and power-seeking) and faithful to actual AI risk drivers to me than the video speed angle? ELK and power-seeking are also useful complements to specific AI risk scenarios.

The video speed framing seems to make the undesirable suggestion that AI ontology will be human-but-faster. I would prefer an example which highlighted the likely differences in ontology. Examples highlighting ontology mismatch have the benefit of neatly motivating the problems of value learning and misaligned proxy objectives.

I am confused about whether the videos are real and exactly how much faster AIs could be run. But I think at the very least it's a promising direction to look for grokkable bounds on how advanced AI will go

It clearly demonstrates what you're talking about in Episode 4x11 of Person Of Interest.

In a nutshell: Our team is trapped somewhere and we see an ASI start calculating to save them. It takes about 10 seconds for ASI and if I remember correctly, it finds the most suitable one out of 800,000 possible situations. It uses security cameras to monitor people, meaning it monitors almost everyone. And it calculates similar actions for all the people it watches

It's crazy to even imagine.

Bizarre coincidence. Or maybe not.

Last night I was having 'the conversation' with a close friend and also found that the idea of speed of action was essential for explaining around the requirement of having to give a specific 'story'. We are both former StarCraft players so discussing things in terms of an ideal version of AlphaStar proved illustrative. If you know StarCraft, the idea of an agent being able to maximize the damage given and received for every unit, minerals mined, and resources expended, the dancing, casting, building, expanding, replenishing to the utmost degree, reveals the impossibility of a human being able to win against such an agent.

We wound up quite hung up on two objections. 1) Well, people are suspicious of AIs already, and 2) just don't give these agents access to the material world. And although we came to agreement on the replies to these objections, by that point we are far enough down the inferential working memory that the argument doesn't strike a chord anymore.

I like using the intuition pump of, AI : Humans :: Human : Apes. Imagine apes had the decision to create humans or not. They can sit there and argue about how humans will share ape values because they're descended from apes. Or how humans pose an existential risk to apes or some such.

Humans may be dangerous because they'll be smarter than us apes. Maybe humans will figure out how to get those bananas at the very top of the tree without risk of falling, then humans will have a massive advantage over apes. Maybe humans will better know how to hide from leopards; they'll be able to hurt apes by attracting leopards to the colony and then hiding. Humans might be dangerous, but if we contain them or ensure that they share ape values then us apes will be better off.

And then humans take over the whole world and apes live in artificial habits entertaining us or survive in the wild only due to our mercy. We're just too stupid to reasonably think of the ways AI will be able to defeat us. We're sitting here with a boxed-AI thinking about the risk of nanotech while the AI is creating irl magic by warping the electric field of the world using just it's transistors.

Like, we're so stupid we don't even know how to spontaneously generate biological life. The upper bound on intelligence is way above where we're at now.

It stands for Eliciting Latent Knowledge [LW · GW].

I'm not a fan of saying that AIs will have a 10 million x speedup relative to humans. That seems very unlikely to happen on this side of the singularity. Probably, future AGI hardware will increasingly resemble [LW · GW] the brain, and AGI's won't have nearly a 10 million x higher serial clock speed advantage compared to humans. 

"human" objects around that could easily be taken apart for, say, biofuel or carbon atoms

This is one aspect of the discussion that never sits right with me: the idea that what might interest a future superintelligence is our "atoms" and not our standing as the only thing that's ever created a superintelligence so far. There are lots of more efficient fuels and more readily obtainable sources of carbon atoms than all the humans scurrying (or lumbering, to take the point of your post) around the earth. 

I suppose the charitable interpretation of this is is a superintelligence will make little distinction between the human and the concrete wall they're standing next to in terms of where it might choose to scoop up some matter?

Transistors can fire about 10 million times faster than human brain cells

Does anyone have a citation for this claim?

Also along these lines, perhaps contrasting the flicker fusion rates of different species could be illustrative as well. Here's a 30-second video displaying the relative perceptions of a handful of species side by side: https://www.youtube.com/watch?v=eA--1YoXHIQ . Additionally, a short section from 10:22 - 10:43 of this other video that incorporates time-stretched audio of birdcalls is fairly evocative: https://www.youtube.com/watch?v=Gvg242U2YfQ .

This reminds me of Eliezer's short story That Alien Message [LW · GW], which is told from the other side of the speed divide. There's also Freitas' "sentience quotient" idea upper-bounding information-processing rate per unit mass at SQ +50 (it's log scale -- for reference, human brains are +13, all neuronal brains are several points away, vegetative SQ is -2, etc).

This is a fantastic idea! it manages to successfully convey how much more powerful an artificial brain could be than a human one.

I can't help pointing out one thing, which is that an AGI trying to take over the world would pretty much need to manipulate/interact with humans, and their reaction time/processing speed would be effectively a bottleneck for the AGI.