I’m a software engineer. I have a blog at niknoble.com.
niknoble
You say “We can’t know how difficult it will be or how many years it will take” Well, why do you seem so confident that it’ll take multiple decades? Shouldn’t you be more epistemically humble / cautious? ;)
Epistemic humility means having a wide probability distribution, which I do. The center of the distribution (hundreds of years out in my case) is unrelated to its humility.
Also, the way I phrased that is a little misleading because I don’t think years will be the most appropriate unit of time. I should have said “years/decades/centuries.”
The only issue I’d take is I believe most people here are genuinely frightened of AI. The seductive part I think isn’t the excitement of AI, but the excitement of understanding something important that most other people don’t seem to grasp.
I felt this during COVID when I realized what was coming before my co-workers etc did. There is something seductive about having secret knowledge, even if you realize it’s kind of gross to feel good about it.
Interesting point. Combined with the other poster saying he really would feel dread if a sage told him AGI was coming in 2040, I think I can acknowledge that my wishful thinking frame doesn’t capture the full phenomenon. But I would still say it’s a major contributing factor. Like I said in the post, I feel a strong pressure to engage in wishful thinking myself, and in my experience any pressure on myself is usually replicated in the people around me.
Regardless of the exact mix of motivations, I think this--
My main hope in terms of AGI being far off is that there’s some sort of circle-jerk going on on this website where everyone is basing their opinion on everyone else, but everyone is basing it on everyone else etc etc
is exactly what’s going on here.
I’m genuinely frightened of AGI and believe there is a ~10% chance my daughter will be killed by it before the end of her natural life, but honestly all of my reasons for worry boil down to “other smart people seem to think this.
I have a lot of thoughts about when it’s valid to trust authorities/experts, and I’m not convinced this is one of those cases. That being said, if you are committed to taking your view on this from experts, then you should consider whether you’re really following the bulk of the experts. I remember a thread on here a while back that surveyed a bunch of leaders in ML (engineers at Deepmind maybe?), and they were much more conservative with their AI predictions than most people here. Those survey results track with the vibe I get from the top people in the space.
Third “fact” at the top of the original post “We’ve made enormous progress towards solving intelligence in the last few years” is somewhat refuted by the rest: if it’s a math-like problem, we don’t know how much progress toward AGI we’ve made in the last few years.
Yeah, it crossed my mind that that phrasing might be a bit confusing. I just meant that
It’s a lot of progress in an absolute sense, and
It’s progress in the direction of AGI.
But I believe AGI is so far away that it still requires a lot more progress.
AGI in our lifetimes is wishful thinking
I give 60% odds it was them.
I’m pretty far in the other direction. I would give 90% odds it was done by the US or with our approval. These are the points that convinced me:
The prior on someone destroying their own infrastructure is pretty low
The US has a clear incentive to weaken Russia’s leverage over our European allies
There are old videos of Joe Biden and Victoria Nuland apparently threatening Nord Stream 2 in the event that Russia invades Ukraine
Also, a counterpoint to your coup-prevention theory. Let’s suppose Putin is worried about defectors in his ranks who may be incentivized to take over in order to turn on the pipeline. In that case, couldn’t Putin remove the incentive by turning it on himself? And wouldn’t that be a strictly better option for him than destroying it?
This got me thinking about how an anonymous actor could prove responsibility. It occurred to me that they could write their bitcoin address into the genome of the modified mosquitos. I don’t know if that’s how gene drives work, but it’s an interesting premise for a sci-fi story in any case.
I think therapy is one of the defining superstitions of our era. Even in communities where people are over the target on most issues, this one always seems to slip through.
I would be surprised if any kind of therapy is more effective than placebo, even the “academic, evidence-based psychotherapy research.”
it is clear these geniuses are capable of understanding things the vast, vast, vast majority of people are not
As the original post suggests, I don’t think this is true. I think that pretty much everyone in this comments section could learn any concept understood by Terry Tao. It would just take us longer.
Imagine your sole purpose in life was to understand one of Terry Tao’s theorems. All your needs are provided for, and you have immediate access to experts whenever you have questions. Do you really think you would be incapable of it?
Agreed. Also, it’s not surprising that the universality threshold exists somewhere within the human range because we already know that humans are right by the cutoff. If the threshold were very far below the human range, then a less evolved species would have hit it before we came about, and they would have been the ones to kick off the knowledge explosion.
I try to remind myself that intelligence is not some magical substance that is slipping through my fingers, but rather a simple algorithm that will eventually be understood. The day is coming when we will be able to add more intelligence to a person as easily as we add RAM to a computer. Viewed in that light, it feels less like some infinitely precious gift whose loss is infinitely devestating.
but there seems to be a very strong similarity between the paradoxes of existence and consciousness as I’ve come to think about them
I’ll admit I’m annoyed to see this because I’m working on a blog post that makes exactly this point. Now I feel unoriginal 😛. Below is the connection I see between the “paradoxes,” copy-pasted from my notes.
The physical world, with nothing extra thrown in, necessitates that people will claim certain aspects of their experience to be non-material, and it gives a satisfying, purely physical explanation for why they do.
The math, with nothing extra thrown in, necessitates that people will claim to be physically real, and it gives a satisfying, purely mathematical explanation for why they do.
If it seems like we’re stuck with a bad situation, reframe it as a positive to cope.
This one will probably kill me because it has prevented us from putting serious resources towards curing aging.
Also (much less importantly) it means we do not put any effort into reducing the amount of paid work people are required to do, even as economic efficiency skyrockets. Shouldn’t we be able to have 20-hour workweeks by now?
But everything is kinda like this. When I translate the abstract concepts in my head into these words that I’m typing, I just do the information processing, I can maybe focus on different aspects of it consciously, but I don’t know what my brain is doing and can’t make a conscious decision to use someone else’s word-generation method instead of my own.
I would say the process that maps concepts to words is outside of me, so the fact that it happens unconsciously is in harmony with my argument. If I’m seeking a word for a concept, it feels like I direct my attention to the concept, and then all of its associations are handed back to me, one of the strongest ones being the word I’m looking for. That is, the retrieval of the word requires hitting an external memory store to get the concept’s associations.
On the other hand, the choice of concept to convey is made by me. I also choose whether to use the first word I find, or to look for a better one. Plus I choose to sit down and write in the first place. Unlike looking up words from my memory, where the words I receive are out of my control, I could have made these choices differently if I wanted to. Thus, they are part of my limited domain within the brain. You could say, “those choices are making themselves,” but then what are people referring to when they say a person did something consciously? There must be a physical distinction between conscious and unconscious actions, and that’s where I suspect you’ll find a reasonable definition of a “self module.”
Another way of putting this is that every process in the brain that can be thought of as conscious, can also be thought of as unconscious if you break it into small pieces.
I agree completely with that. But the visual processing that occurs to produce optical illusions cannot be thought of as conscious, period. Anything I would call conscious excludes that visual processing layer. It is not a “perfectly valid component of the thinking I do,” because it happens before I get access to the information to think about it.
If you put on a pair of warped glasses that distort your vision, you would not call those glasses part of your thinking process. But when the visual information you are receiving is warped in exactly the same way due to an optical illusion, you say it’s your own reasoning that made it like that. As far as I’m concerned, the only real difference is that you can’t remove your visual processing system. It’s like a pair of warped glasses that is glued to your face.
To be fair, this might be just another semantic argument. Maybe if we both understood the brain in perfect detail, we would still disagree about whether to call some specific part of it “us.” Or maybe I would change my mind at that point. I get the feeling you’ve investigated the brain more than me, and maybe you reach a point in your learning where you’re forced to discard the default model. Still, I think the position I’ve laid out has to be the default position in absence of any specific knowledge about the brain, because this is the model which is clearly suggested by our day-to-day experience.
There is no inner observer inside the brain. The brain is where our thoughts are (or representations of those thoughts), but there isn’t some much-more-specific-than-that place in the brain that’s “us” while the rest is merely a pile of tagalong grey matter.
I agree with the general thrust of the post, and with your comment. However, I’m not sure I buy this particular piece.
My position is that I am a submodule in my brain, and I communicate with the rest of the brain through a limited interface. Maybe I’m not physically distinct from the rest of the brain, off in my own little section, but I’m logically distinct.
At the very least, there is a visual processing layer in my brain that is not part of me. I know this because visual data sometimes gets modified before it gets from my eyes to me. (For example, when looking at an optical illusion or hallucinating on a drug.) I have no awareness of or control over this preprocessing.
On the output side, I have more control. If I send a command to a muscle, rarely will it be vetoed by some later process. I take it that’s because I’m the executive module, and my whole purpose is to decide muscle movements. Nothing else in the brain is qualified to override my choices on that front.
However, there are some exceptions where my muscles will move in a way that I didn’t choose, presumably at the behest of another part of my brain which is not me. An example is the hanger reflex, where I put a clothes hanger around my head, and my head turns automatically. Or dumb things like my heartbeat, my stomach, or my breathing while asleep. I am only needed to govern the muscle movements that require intelligence, the movements we call “voluntary.”
If I was my entire brain, then what would be the difference between a voluntary and an involuntary brain-induced action?
Consider this problem: Are there are an infinite number of 9s in the digits of pi? The answer is obviously yes. The only way it could be no is if pi interacts in some strange way with base-10 representations, and pi has nothing to do with base-10.
But how do you prove that no such interaction exists? You have to rule out an endless number of possible interactions, and even then there could be some grand conspiracy between pi and base-10, hiding in the places you haven’t yet looked.
Proving the absense of an interaction between two areas of math is much harder than proving its presence. If you want to prove presence, you can just find the interaction and explain it. But you can’t “find an absence.”
Most of the hard math problems turn out to have this issue at their core. If you dig into Collatz, you find that it’s very likely to be true. The only way it could be false is if there’s an undiscovered conspiracy between parities of integers and the collatz map. How to prove there is no conspiracy?
Unless humanity destroys itself first, something like Horizon Worlds will inevitably become a massive success. A digital world is better than the physical world because it lets us override the laws of physics. In a digital world, we can duplicate items at will, cover massive distances instantaneously, make crime literally impossible, and much, much more. A digital world is to the real world as Microsoft Word is to a sheet of paper. The digital version has too many advantages to count.
Zuckerberg realizes this and is making a high-risk bet that Meta will be able to control the digital universe in the same way that Apple and Google control the landscape of mobile phones. For example, imagine Meta automatically taking 1% of every monetary transaction in the universe. Or dictating to corporate rivals what they are allowed to do in the universe, gaining massive leverage over them. Even if Zuckerberg is unlikely to succeed (and it’s still very unclear what direction the digital universe will evolve), he knows the potential payoff is staggering and calculates that it’s worth it. That’s why he’s investing so heavily in VR, and Horizon Worlds in particular.
As for the aesthetics of Horizon Worlds being creepy, boring, or ugly, there are 2 factors to keep in mind.
First, VR hardware and software are in their infancy and you simply can’t have very crisp graphics at this stage. That is fine according to the philosophy of modern tech companies. Just ship a minimum viable product, start getting users, and react to user feedback as you go. If Horizon Worlds succeeds, it will look far better in 20 years than it does today.
Second, Horizon may get attacked on the internet for being sterile and lifeless, but internet commenters are not the people who are putting direct pressure on Zuckerberg. Rather, he is surrounded by employees and journalists whose primary complaint is that Horizon Worlds is not sterile enough. I’m sure you’ve seen the articles: Harmful language is going unpunished, women are being made to feel uncomfortable by sexual gestures. Considering that Zuckerberg receives a constant barrage of these criticisms now, can you imagine the kind of heat he would get if he made Horizon more like VRChat, with its subversive culture and erotic content?
I agree that this is probably a reason for the greater harm to women, but I don’t think it gets to the heart of it.
Suppose that instead of rape, our culture portrayed some benign, non-sexual experience as deeply harmful. Say, being exposed to the color orange as a kid. In that case, would you predict men or women to be more harmed by having seen orange? If you predict women (as I would), then the explanation has to be more general than evolved attitudes towards sex.
My theory is that it comes down to influenceability. When an authority figure says that something is true, a man is more likely to note that he must act like it’s true, but reserve an inner skepticism; whereas a woman is more likely to accept it wholeheartedly.
For example, it’s easier to imagine a man proactively (without outside influence)...
doubting his religion
doubting the benefits of hand-washing
doubting that perpetual motion is impossible
- Jul 21, 2022, 1:34 PM; 18 points) 's comment on Sexual Abuse attitudes might be infohazardous by (
I mean, plenty of companies in our world give variable salaries based on interview performance. Once you have that the rest follows.
Another alternative: There could be companies that agree to match your highest competing offer. This also exists in our world and would explain the effect.
Maybe there is an aspect of randomness in every salary offer. Sometimes companies will overoffer/underoffer based on their impressions of the candidate. By applying to more places, the men have more opportunities to get lucky with high offers, which they are then likely to accept.
And insofar as your distribution has a close median, you have high confidence that it’s not coming later. Any point about humility cuts both ways.
The difference between those technologies and AGI is that AGI is not remotely well-captured by any existing computer program. With image generation and self-driving, we already have decent results, and there are obvious steps for improvement (e.g. scaling, tweaking architectures). 5-minute videos are similar enough to images that the techniques can be reasonably expected to carry over. Where is the toddler-level, cat-level, or even bee-level proto-agi?