Posts
Comments
What makes you confident that AI progress has stagnated at OpenAI? If you don’t have the time to explain why I understand, but what metrics over the past year have stagnated?
What if Trump is channeling his inner doctor strange and is crashing the economy in order to slow AI progress and buy time for alignment? Eliezer calls for an AI pause, Trump MAKES an AI pause. I rest my case that Trump is the most important figure in the history of AI alignment.
This is an uncharitable interpretation, but “good at increasingly long tasks which require no real cleverness” seems economically valuable, but doesn’t seem to be leading to what I think of as superintelligence.
How does this account for the difficulty of the tasks? AFAIK even reasoning models still struggle with matrix reasoning. And most matrix puzzles (even difficult ones) are something you can do in 15-30 seconds, occasionally 4-5 minutes for sufficiently challenging ones. But even in those cases you usually figure out what to look for in the first 30-60 seconds and then spend the rest of the time on drudge.
So current agents might be capable of the 1 minute task “write a hello world program,” while not being capable of the 1 minute task “solve the final puzzle on Mensa DK.”
And if that’s the case, then agents might be capable of routine long-horizon tasks in the future (whatever that means), while still being incapable of more OOD achievements like “write Attention is all you need.”
What am I missing?
Oh I was actually hoping you’d reply! I may have hallucinated the exact quote I mentioned but here is something from Ulam: “Ulam on physical intuition and visualization,” it’s on Steve Hsu’s blog. And I might have hallucinated the thing about Poincaré being tested by Binet, that might just be an urban legend I didn’t verify. You can find Poincaré’s struggles with coordination and dexterity in “Men of Mathematics,” but that’s a lot less extreme than the story I passed on. I am confident in Tao’s preference for analysis over visualization. If you have the time look up “Terence Tao” on Gwern’s website.
I’m not very familiar with the field of neuroscience, but it seems to me that we’re probably pretty far from being able to provide a satisfactory answer to these questions. Is that true from your understanding of where the field is at? What sorts of techniques/technology would we need to develop in order for us to start answering these questions?
From what I understand, JVN, Poincaré, and Terence Tao all had/have issues with perceptual intuition/mental visualization. JVN had “the physical intuition of a doorknob,” Poincaré was tested by Binet and had extremely poor perceptual abilities, and Tao (at least as a child) mentioned finding mental rotation tasks “hard.”
I also fit a (much less extreme) version of this pattern, which is why I’m interested in this in the first place. I am (relatively) good at visual pattern recognition and math, but I have aphantasia and have an average visual working memory. I felt insecure about this for a while, but seeing that much more intelligent people than me had a similar (but more extreme) cognitive profile made me feel better.
Does anybody have a satisfactory explanation for this profile beyond a simplistic “tradeoffs” explanation?
Edit: Some claims about JVN/Poincare may have been hallucinated, but they are based at least somewhat on reality. See my reply to Steven
This is why I don’t really buy anybody who claims an IQ >160. Effectively all tested IQs over 160 likely came from a childhood test or have an SD of 20 and there is an extremely high probability that the person with said tested iq substantially regressed to the mean. And even for a test like the WAIS that claims to measure up to 160 with SD 15, the norms start to look really questionable once you go much past 140.
I think I know one person who tested at 152 on the WISC when he was ~11, and one person who ceilinged the WAIS-III at 155 when he was 21. And they were both high-achieving, but they weren’t exceptionally high-achieving. Someone fixated on IQ might call this cope, but they really were pretty normal people who didn’t seem to be on a higher plane of existence. The biggest functional difference between them and people with more average IQs was that they had better job prospects. But they both had a lot of emotional problems and didn’t seem particularly happy.
This just boils down to “humans aren’t aligned,” and that fact is why this would never work, but I still think it’s worth bringing up. Why are you required to get a license to drive, but not to have children? I don’t mean this in a literal way, I’m just referring to how casual the decision to have children is seen by much of society. Bringing someone into existence is vastly higher stakes than driving a car.
I’m sure this isn’t implementable, but parents should at least be screened for personality disorders before they’re allowed to have children. And sure that’s a slippery slope, and sure many of the most powerful people just want workers to furnish their quality of life regardless of the worker’s QOL. But bringing a child into the world who you can’t properly care for can lead to a lifetime of avoidable suffering.
I was just reading about “genomic liberty,” and the idea that parents would choose to make their kids iq lower than possible, that some would even choose for their children to have disabilities like them is completely ridiculous. And it just made me think “those people shouldn’t have the liberty of being parents.” Bringing another life into existence is not casual like where you work/live. And the obligation should be to the children, not the parents.
How far along are the development of autonomous underwater drones in America? I’ve read statements by American military officials about wanting to turn the Taiwan straight into a drone-infested death trap. And I read someone (not an expert) who said that China is racing against time to try and invade before autonomous underwater drones take off. Is that true? Are they on track?
MuZero doesn’t seem categorically different from AlphaZero. It has to do a little bit more work at the beginning, but if you don’t get any reward for breaking the rules: you will learn not to break the rules. If MuZero is continuously learning then so is AlphaZero. Also, the games used were still computationally simple, OOMs more simple than an open-world game, let alone a true World-Model. AFAIK MuZero doesn’t work on open-ended, open-world games. And AlphaStar never got to superhuman performance at human speed either.
hi, thank you! i guess i was thinking about claims that "AGI is imminent and therefore we're doomed." it seems like if you define AGI as "really good at STEM" then it is obviously imminent. but if you define it as "capable of continuous learning like a human or animal," that's not true. we don't know how to build it and we can't even run a fruit-fly connectome on the most powerful computers we have for more than a couple of seconds without the instance breaking down: how would we expect to run something OOMs more complex and intelligent? "being good at STEM" seems like a much, much simpler and less computationally intensive task than continuous, dynamic learning. tourist is great at codeforces, but he obviously doesn't have the ability to take over the world (i am making the assumption that anyone with the capability to take over the world would do so). the second is a much, much fuzzier, more computationally complex task than the first.
i had just been in a deep depression for a while (it's embarassing, but this started with GPT-4) because i thought some AI in the near future was going to wake up, become god, and pwn humanity. but when i think about it from this perspective, that future seems much less likely. in fact, the future (at least in the near-term) looks very bright. and i can actually plan for it, which feels deeply relieving to me.
Apologies in advance if this is a midwit take. Chess engines are “smarter” than humans at chess, but they aren’t automatically better at real-world strategizing as a result. They don’t take over the world. Why couldn’t the same be true for STEMlord LLM-based agents?
It doesn’t seem like any of the companies are anywhere near AI that can “learn” or generalize in real time like a human or animal. Maybe a superintelligent STEMlord could hack their way around learning, but that still doesn’t seem the same as or as dangerous as fooming, and it also seems much easier to monitor. Does it not seem plausible that the current paradigm drastically accelerates scientific research while remaining tools? The counter is that people will just use the tools to try and figure out learning. But we don’t know how hard learning is, and the tools could also enable people to make real progress on alignment before learning is cracked.
You’re probably right but I guess my biggest concern is the first superhuman alignment researchers being aligned/dumb enough to explain to the companies how control works. It really depends on if self-awareness is present as well.
what is the plan for making task-alignment go well? i am much more worried about the possibility of being at the mercy of some god-emperor with a task-aligned AGI slave than I am about having my atoms repurposed by an unaligned AGI. the incentives for blackmail and power-consolidation look awful.
I honestly think the EV of superhumans is lower than the EV for AI. sadism and wills to power are baked into almost every human mind (with the exception of outliers of course). force multiplying those instincts is much worse than an AI which simply decides to repurpose the atoms in a human for something else. i think people oftentimes act like the risk ends at existential risks, which i strongly disagree with. i would argue that everyone dying is actually a pretty great ending compared to hyperexistential risks. it is effectively +inf relative utility.
with AIs we're essentially putting them through selective pressures to promote benevolence (as a hedge by the labs in case they don't figure out intent alignment). that seems like a massive advantage compared to the evolutionary baggage associated with humans.
with humans you'd need the will and capability to engineer in at least +5sd empathy and -10sd sadism into every superbaby. but people wouldn't want their children to make them feel like shitty people so they would want them to "be more normal."
I think that people don’t consider the implications of something like this. This seems to imply that the mathematical object of a malevolent superintelligence exists, and that conscious victims of said superintelligence exist as well. Is that really desirable? do people really prefer that to some sort of teleology?
Yeah something like that, the ASI is an extension of their will.
This is just a definition for the sake of definition, but I think you could define a human as aligned if they could be given an ASI slave and not be an S-risk. I really think that under this definition, the absolute upper bound of “aligned” humans is 5%, and I think it’s probably a lot lower.
I should have clarified, I meant a small fraction and that that is enough to worry.
I agree. At least I can laugh if the AGI just decides it wants me as paperclips. There will be nothing to laugh about with ruthless power-seeking humans with godlike power.
That sounds very interesting! I always look forward to reading your posts. I don’t know if you know any policy people, but in this world, it would need to be punishable by jail-time to genetically modify intelligence without selecting for pro-sociality. Any world where that is not the case seems much, much worse than just getting turned into paper-clips.
I certainly wouldn’t sign up to do that, but the type of individual I’m concerned about likely wouldn’t mind sacrificing nannies if their lineage could “win” in some abstract sense. I think it’s great that you’re proposing a plan beyond “pray the sand gods/Sam Altman are benevolent.” But alignment is going to be an issue for superhuman agents, regardless of if they’re human or not.
I’m sure you’ve already thought about this, but it seems like the people who would be willing and able to jump through all of the hoops necessary would likely have a higher propensity towards power-seeking and dominance. So if you don’t edit the personality as well, what was it all for besides creating a smarter god-emperor? I think that in the sane world you’ve outlined where people deliberately avoid developing AGI, an additional level of sanity would be holding off on modifying intelligence until we have the capacity to perform the personality edits to make it safe.
I can just imagine this turning into a world where the rich who are able to make their children superbabies compete with the rest of the elite over whose child will end up ruling the world.
I’m sorry but I’d rather be turned into paper-clips then live in a world where a god-emperor can decide to torture me with their AGI-slave for the hell of it. How is that a better world for anyone but the god-emperor? But people are so blind and selfish, they just assume that they or their offspring would be god-emperor. At least with AI people are scared enough that they’re putting focused effort into trying to make it nice. People won’t put that much effort into their children.
I mean hell, figuring out personality editing would probably just make things backfire. People would choose to make their kids more ruthless, not less.
How much do people know about the genetic components of personality traits like empathy? Editing personality traits might be almost as or even more controversial than modifying “vanity” traits. But in the sane world you sketched out this could essentially be a very trivial and simple first step of alignment. “We are about to introduce agents more capable than any humans except for extreme outliers: let’s make them nice.” Also, curing personality disorders like NPD and BPD would do a lot of good for subjective wellbeing.
I guess I’m just thinking of a failure mode where we create superbabies who solve task-alignment and then control the world. The people running the world might be smarter than the current candidates for god-emperor, but we’re still in a god-emperor world. This also seems like the part of the plan most likely to fail. The people who would pursue making their children superbabies might be disinclined towards making their children more caring.
>be me, omnipotent creator
>decide to create
>meticulously craft laws of physics
>big bang
>pure chaos
>structure emerges
>galaxies form
>stars form
>planets form
>life
>one cell
>cell eats other cell, multicellular life
>fish
>animals emerge from the oceans
>numerous opportunities for life to disappear, but it continues
>mammals
>monkeys
>super smart monkeys
>make tools, control fire, tame other animals
>monkeys create science, philosophy, art
>the universe is beginning to understand itself
>AI
>Humans and AI together bring superintelligence online
>everyone holds their breath
>superintelligence turns everything into paper clips mfw infinite kek
I think Noah Carl was coping with the “downsides” he listed. Loss of meaning and loss of status are complete jokes. They are the problems of people who don’t have problems. I would even argue that focusing on X-risks rather than S-risks is a bigger form of cope than denying AI is intelligent at all. I don’t see how you train a superintelligent military AI that doesn’t come to the conclusion that killing your enemies vastly limits the amount of suffering you can inflict upon them.
Edit: I think loss of actual meaning, like conclusive proof we're in a dysteleology, would not be a joke. But I think that loss of meaning in the sense of "what am I going to do if I can't win at agent competition anymore :(" feels like a very first-world problem.
Everything feels so low-stakes right now compared to future possibilities, and I am envious of people who don’t realize that. I need to spend less time thinking about it but I still can’t wrap my head around people rolling a dice which might have s-risks on it. It just seems like a -inf EV decision. I do not understand the thought process of people who see -inf and just go “yeah I’ll gamble that.” It’s so fucking stupid.
Hi Steven! This is an old post, so you probably won't reply, but I'd appreciate it if you did! What do you think might be going on in the brains of schizophrenics with high intelligence? I know schizophrenia is typically associated with MRI abnormalities and lower intelligence, but this isn't always the case! At least for me, my MRI came back normal, and my cognitive abilities were sufficient to do well in upper level math courses at a competitive university: even during my prodromal period. I actually deal with hypersensitivity as well, so taking a very shallow understanding of your post and applying it to me, might my brain have a quirk that enables strong intracircuit communication (resulting in strong working memory and processing speed and hypersensitivity), but not intercircuit communication (resulting in hallucinations/paranoia as downsides but a high DAT score as an upside?)?
I see no reason why any of these will be true at first. But the end-goal for many rational agents in this situation would be to make sure 2 and 3 are true.
That makes sense. This may just be wishful thinking on my part/trying to see a positive that doesn't exist, but psychotic tendencies might have higher representation among the population you're interested in than the trend you've described might suggest. Taking the very small, subjective sample that is "the best" mathematician of each of the previous four centuries (Newton, Euler, Gauss, and Grothendieck), 50% of them (Newton and Grothendieck) had some major psychotic experiences (admittedly vastly later in life than is typical for men).
Again, I'm probably being too cautious, but I'm just very apprehensive about approaching the creation of sentient life with the attitude that increased iq = increased well-being. If that intution is incorrect, it would have catastrophic consequences.
"I don't think you'll need to worry about this stuff until you get really far out of distribution." I may sound like I'm just commenting for the sake of commenting but I think that's something you want to be crystal clear on. I'm pessimistic in general and this situation is probably unlikely but I guess one of my worst fears would be creating uberpsychosis. Sounding like every LWer, my relatively out of distribution capabilities made my psychotic delusions hyper-analytic/1000x more terrifying & elaborate than they would have been with worse working memory/analytic abilities (once I started ECT I didn't have the horsepower to hyperanalyze existence as much). I guess the best way to describe it was that I could feel the terror of just how bad -inf would truly be as opposed to having an abstract/detached view that -inf = bad. And I wouldn't want anyone else to go through something like that, let alone something much scarier/worse.
This might be a dumb/not particularly nuanced question, but what are the ethics of creating what would effectively be BSI? Chickens have a lot of health problems due to their size, they weren't meant to be that big. Might something similar be true for BSI? How would a limbic system handle that much processing power: I'm not sure it would be able to. How deep of a sense of existential despair and terror might that mind feel?
TLDR: Subjective experience would likely have a vastly higher ceiling and vastly lower floor. To the point where a BSI's (or ASI's for that matter) subjective experience would look like +/-inf to current humans.
Making the (tenuous) assumption that humans remain in control of AGI, won't it just be an absolute shitshow of attempted power grabs over who gets to tell the AGI what to do? For example, supposing OpenAI is the first to AGI, is it really plausible that Sam Altman will be the one actually in charge when there will have been multiple researchers interacting with the model much earlier and much more frequently? I have a hard time believing every researcher will sit by and watch Sam Altman become more powerful than anyone ever dreamed of when there's a chance they're a prompt away from having that power for themselves.