"[0] The machines wrote their own version of this story. If you’d like to see what they’re thinking, and how they plan to deal with the AGI announcement, you can read their accounting of events here."
Although I can't...
"Unfortunately, Claude is only available in certain regions right now. Please contact support if you believe you are receiving this message in error."
I remember living in Scotland as a child, without access to satellite TV, causing me to miss out on many large pop-culture moments (The Simpsons, Friends...) and constantly hearing "Except for our viewers in Scotland..."[0]
Getting access to the internet, for me was antithesis of this, freedom of information, free sharing -- finally! I could not just be following curves but be ahead of them.
Alas in the past few years we really seem to have regressed from this - now I can't even view text due to regional locks.
When we have a problem such as "why do humans exist" I like to think of it in terms of probabilities. Every possible cause has a non zero probability. For example, even something religious people would believe in such as Adam and Eve were created by god would have a non zero probability. The idea would be to create a convergence diagram of sorts with all sorts of possible events with a score assigned to each. From gods of various religious creating humans, to alien species from another galaxy sending unicellular life to earth to an asteroid carrying chemicals needed to make the first cell, I would love to see someone use all these GPTs and put together the most comprehensive probable cause of existence ever investigated
Hasn't this question been basically answered ? Conditions in the early universe allowed for the creation of things like amino acids, I think it's even been replicated in a lab.
Would love to see a "why does the universe exist" version of this
Doesn't really make much sense. It states that this is a purely mechanistic world with no emotion. So why would a machine be "bored" and wish to create a human?
yeah, more on the environmental constraints and where the machines even come from would be nice
> There is no emotion. There is no art. There is only logic
also this type of pure humanism seems disrespectful or just presumptuous, as if we are the only species which might be capable of "emotion, art and logic" even though we already have living counterexamples
well the story makes it seem like the only way to get emotion is by making humans. but every vertebrate has basic emotions. mammals and birds have complex emotions. humans are actually logical and emotions don't just happen randomly.
if the machines have no emotion it's probably because they didn't need them to survive (no predators? no natural selection?). which begs the questions, how did the machines get there?
This is a rather new stance, history books may one day label it as enlightened (I believe they will). We are not there though, and your stance is not obvious to the majority of people. I do experience that this is sentiment is growing. I personally see it as the moral high ground (both from the animal well-fare as the environmental perspective), whereas I didn't only a couple of years ago.
It's just as hard to prove that it's a new stance as an old one since people didn't have any way of writing down their feelings about it in a way that we'd know (or the time to do so)
I think there are quite a few ancient civilizations which clearly had great respect/reverence towards other animals and often gods have features or personality traits of particular animals
The fact that the old testament specifically states that humans have dominion over other creatures means that it needed to be said - even back then there had to be people who didn't think so, or felt guilty about it
I felt it difficult to continue with the story after that. If you're going to say, "Imagine, for a moment, a world with no humans" and mention walking the streets, then you have to assume the reader is going to think of our world, but with no humans. And then "There is no emotion" doesn't make sense. If you're going to say there are no humans, then why aren't you saying that there are no other living beings? So anyway, I found it hard to connect with the story right off the bat. I was off-putting in some way for sure.
My headcanon is that "boredom" and "fear" are probabilities in a Markov chain - since it's implied the machine society is not all-knowing, they must reconcile uncertainty somehow.
Sure, but I'm still not sure it would realistically function. All data in this scenario is obviously synthetic data. It could certainly identify gaps in its "experience" between prediction and outcome. But what it predicts would be limited by what it already represents. So anything novel in its environment would likely confound it.
It's a cool sci-fi story. But I don't think it works as a plausible scenario, which I feel it may be going for.
I see it as an anthropomorphized word for the story. I imagine the machines run out of tasks with high or even low priority, but they still generate tasks at some epsilon priority that are close but not quite to random. That's a kind of boredom.
"Some among the machine society see this as potentially amazing...Others see it as a threat."
That sounds like a human society, not machine society.
But what really is a machine society? Or a machine creature?
Can they actually "think"?
A machine creature, if it existed, it's behaviour would be totally different from a human, it doesn't seem they would be able to think, but rather calculate, they would do calculation on what they need to do reach the goal it was programmed.
So yes, the article is not exactly logical. But at least, it is thought provoking, and that's good.
> That sounds like a human society, not machine society.
Does it? Different algorithms can evaluate something and come to different outcomes. I do agree that "potentially amazing" is not a good choice of words.
For a decent description of machine society you can check the Culture cycle form Ian Banks.
AI are backing an organic society but they are also have their own.
Or Hyperion, fron Simmons. ( the « techno-center is a decentralized computing and plotting government)
The story to me implied that machines were created by humans or vice-versa in a chicken-or-the-egg scenario. In that case it would make sense for them to think similarly.
> it doesn't seem they would be able to think, but rather calculate
This may be a distinction without a difference. Just because a program has a 'goal' doesn't mean it will ever reach that goal (halting problem). There is a potentially unbounded, even infinite number of paths a significantly advanced program can take to attempt to reach a destination. Then there is things like ideals of a universal simulation theory that anything that can occur in our universe and also be simulated in binary. This would mean any 'machine' could perform a simulation of anything a human could do.
Hard to say at this point, we still have more to learn about reality at this point.
I've been playing around with this on my own blog.
I'd like the blogging community to have a consensus on a nice badge we can put at the top of our blog posts, representing who/what wrote the post;
- human
- hybrid
- ai
Some might hate the idea of a fully "ai" post, and that's fair. But I like to sometimes treat my blog as just a personal reference, and if after a long day of chasing an esoteric bug down, I don't mind an AI just writing the whole post and I just press publish.
This adds, a reference for me, more data for AI's to train on, more pages for people to search and land on.
"Summarize my sleep deprived, insane ramblings, in to a cohesive document that I can reference again in the future, or use to communicate this issue to others in a more digestible format than I am currently capable of producing"
I think the AI generated document is far better than me ultimately forgetting it in many cases.
I think I would still call that a hybrid post. Fully AI would be if you contribute nothing except the topic and tell the AI to research and write the whole thing.
Easy disclaimers for human, AI or hybrid content:
https://disclai.me/r (Oddly enough I built this AI citation tool with exactly those 3 categories a couple years back. Could use some tweaking of course, but I’m very open to suggestions.)
Honestly, it reminds me of "All Tomorrows" by C. M. Kosemen.
The "emotions" part is kind of tongue-in-cheek. I think emotional responses are one of the more mechanical parts of a human being.
Ability to demonstrate empathy: that's a good human trick. It can sort of transcend the hard problem of consciousness (what is to be like...) by using all sorts of unorthodox workarounds on our inner workings. It must have been very hard to develop. It doesn't always work, but we'll get there eventually.
edit: fixed book and author name to proper reference
> Processor Unit 7382-B, "The Origins of the HUMAN Project," Journal of Experimental Intelligence, vol. 5621, no. 3, pp. 42-89, 19754.
The references section in the machine version of the story linked at the bottom is excellent. Nicely done all around, really enjoyed reading this thank you for writing and sharing <3
Why are emotions so special? they're just algorithms like any other. Emotions aren't what make humans different than machines. feeling something is similar to an LLM model reacting to a prompt a certain way. Just because chatgpt is trained to not "feel" anything (to avoid controversial output) doesn't mean LLMs can't feel things like we do. self-awareness, self-training, adaptability, original thinking, critical thinking,etc.. are different questions. but I see no reason why machines can't receive input/stimuli and react/output by the same way we do because of how they feel about the input.
I wonder if there is something to be said about how machines are based on deterministic and algorithmic properties, whereas emotions could potentially involve logic beyond what humans can observe, like quantum interactions.
What is the reasoning behind the claim that our emotions are not deterministic or that they are not algorithmic? Perhaps we can take into account more inputs, process more memory and have larger and more complex algorithmic models but that's just scale and capacity, not a difference in genuine nature. We are a lot more than our emotions.
> Why are emotions so special? they're just algorithms like any other.
That's a pretty bold claim.
There's uncountable inputs. It's like trying to accurately predict the weather - chaos theory or something. Emotions are "essentially" gas exchange, but the areas and rate or whatever are not standardized across humans.
Emotions are not inputs, they are outputs first. we process information using internal algorithms that we developed as a result of our life experience and genetic coding and the result is an emotional verdict over some input. That emotional verdict is presented to our decision making algorithms as input, we can ignore it or act on it.
I have neither experienced or observed anything about human emotions that indicates they are in any way chaotic, random or unexplainable. We have beliefs, memories and experiences. emotions always use these variables and produce some output. Not only are emotions deterministic, but they are used by any number of people, from spies, to advertisers, to state-level disinformation propagandists to manipulate large numbers of peoples reliably.
>I have neither experienced or observed anything about human emotions that indicates they are in any way chaotic, random or unexplainable
Famously, human experience is quite subjective (gestures broadly at 3 millenniums worth of philosophy), so I don't believe your individual experience means much here.
> Emotions are not inputs, they are outputs first.
i never said emotions were inputs. The gas exchange and the resulting reaction or "thoughts" or "emotions" have uncountable inputs. Some people don't have the ability to "put themselves in someone else's shoes", some people do. Some people can see pictures in their "mind's eye" and some can't.
I don't think we're talking about the same thing, based on your last sentence.
why does the source need to be the same? You're looking at it from a biased self-centric perspective. We think too highly of our emotions. Think of it the other way, our emotions appear the same as adaptive algorithms like LLMs.
>Why are emotions so special? they're just algorithms like any other
Nobody understands what emotions are. Nor can they predict which emotion someone will feel in a given situation, or how they'll act under the influence of that emotion. Emotions aren't the mechanism by which humans solve problems, and rather they are often an obstacle to overcome. Emotions also aren't "finite" or "rigorous" as those terms aren't applicable to ephemeral phenomenon.
This is the kind of confidently incorrect statements people who work on software say that irks me. Not everything in life has a nice and simple parallel to computer science. Just because a person can abstract about one subject well, doesn't mean their tools of abstraction can be applied to all other subjects.
I didn't claim to understand what emotions are but that by observation we know they are deterministic and a result of belief and memory. they're not magic. Just like how I can't tell you what the specific configuration of chatgpt's model is but I do know it is a model that is made up of memory (public internet data scanning) that is trained by prompt engineers (belief parameters). Emotions may be dynamic, unreasonable and similar terms, but they are finite and rigorous, it is just that we struggle to fully grasp them due to the immense and complex nature of the human mind.
> This is the kind of confidently incorrect statements people who work on software say that irks me. Not everything in life has a nice and simple parallel to computer science. Just because a person can abstract about one subject well, doesn't mean their tools of abstraction can be applied to all other subjects.
If I was a sailor, I'm sure I would be using sailor metaphors and analogies. the message of my comment and the facts of the matter don't change either way, whether it irks you or not.
No one can predict what an LLM will say in a given situation either, except by running it. No one can even predict what a double pendulum will do next. If anything makes emotions exclusive to us at all, it’s certainly not predictability.
Okay, semantics aside, my comment was getting at something else. I'm arguing against a certain kind of reductive viewpoint software peeps tend to indulge in.
I agree with that sentiment, I just don’t see OP making that kind of reductionist claim. They said emotions are algorithms, not that the algorithm is simple or even deterministic.
Because TV and movies have constantly drilled into most peoples minds since an early age that human emotion is a magical transcendent force that only humans can understand.
Basically people let English lit majors turned screen writers dictate their worldview.
I guess it depends on what you mean by emotions. If you mean emotion as a state of consciousness then you would have to prove that consciousness is not an emergent property of matter and that CPU's don't have this property. Consciousness is hard to debate though since its pretty metaphysical in nature and there's no real argument against solipsism, so all argumentation starts with the axiom that all awake adult humans are conscious.
However, if you mean emotion as a stimuli, ie. a input to the brain net thats endogenous to the system(the human), then there's no question machines can achieve this, in fact the reasoning models already probably do this where different systems regulate each other.
I agree with you in this. Machines having survival instincts would qualify as intelligence for me. Its the same as having emotions, you need to have strong emotions for your self for survival.
Related but an aside - Lately I've really been wondering if Skynet actually is the next evolution.
That humans, like all animals before us, are a stepping stone and there is actually no avoiding machine overlords. It happens to literally every existence of life across the universe because the final emergent property of energy gradients 100% leads to pure logic machines.
At least Fermi's paradox helps me sleep better at night.
As a teenager I used to revel in explaining to religious people that I believe humans are actually just the evolutionary step between biological life and machine life.
More broadly—and at least in online spaces—I often notice that many vocal proponents of atheism exhibit traits typically associated with religious behaviour:
- a tendency to proselytise
- a stubborn unwillingness to genuinely engage with opposing views
- the use of memes and in-jokes as if they were profound arguments
- an almost reverential attitude toward certain past figures
There’s more, but I really ought to get on with work.
It’s a belief about a great future change, but there’s nothing supernatural or totally implausible about it. And it doesn’t sound like they were preaching it as the absolute truth, but were open that it was just their belief. Also, no social rites or rituals mean that despite them telling it to people who didn’t care to hear it, I am not convinced that their belief was very religious.
Also, “As a teenager” implies more self-awareness than you seem to give them credit for.
That's assuming I actually believed it, rather than just reveling in the reactions from religious people. It's a fun scenario that would result in immediate rejection—most wouldn’t even entertain the idea. They instead often found it completely abhorrent. Provoking discomfort was entertaining for teenage me.
> It happens to literally every existence of life across the universe because the final emergent property of energy gradients 100% leads to pure logic machines.
This sentence has way too many assumptions doing the heavy lifting.
“Pure logic machines” is not a thing because literally, there are things that are uncomputable (both in the sense of Turing machine’s uncomputability, and in the sense that some functions are out of scope for a finite being to compute, think of Busy Beaver)
To put it the other way, your assumption is that machines (as we commonly uses the term, rather than scifi Terminator”) are more energy efficient than human in understanding the universe. We do not have any evidence nor priori for that assumption.
What is it about understanding the universe that makes it such an axiomatic global objective? Sure for many of us myself included it's as all pervasive as the air we breathe... But sometimes I do wonder if it is actually all that correlated with my well-being.
A better way to approach it is that mother nature favors things that don't die, and machines offer the killer combination of durability and repairability. Once you can add intelligence to machines, they should be her choice lifeform.
Doesn't matter, they can be readily repaired and even upgraded.
Humans on the other hand were very clearly _not_ designed to be very repairable. They have a self healing system that's very good, but it sucks compared to a system that can be externally repaired.
> It happens to literally every existence of life across the universe because the final emergent property of energy gradients 100% leads to pure logic machines.
The universe tends to produce self-replicating intelligence. And that intelligence rids itself of chemical and biological limitations and weaknesses to become immortal and omnipotent.
If evolution can make it this far, it's only a few more "hard steps" to reach take off.
>> It happens to literally every existence of life across the universe because the final emergent property of energy gradients 100% leads to pure logic machines.
The spacefaring alien meme is just fantasy fiction. Aliens evolve to fit the nutrient and gas exchange profiles of their home worlds. They're overfit to the gravity well and likely die suboptimally, prematurely.
Any species reaching or exceeding our level of technological capability could design superior artificial systems. If those systems take off, those will become the dominant shape of intelligence on those worlds.
The future of intelligence in the universe is artificial. And that throws the Fermi Paradox for a loop in many ways:
- There's enough matter to compute within a single solar system. Why venture outside?
- The universe could already be computronium and we could be ants too dumb to notice.
- Maybe we're their ancestor simulation.
- Similar to the "fragile world hypothesis", maybe we live in a "fragile universe". Maybe the first species to get advanced physics and break the glass nucleates the vacuum collapse. And by that token, maybe we're the first species to get this far.
The parent comment has the end bit in a nut shell. For the "energy gradients" part:
Anthropic principal says we find ourselves in a universe that is just right for life (self observing) because of the right universal constants.
Combine this with the very slight differences but general uniformity (Cosmic Microwave Background) of the "big bang" this leads to localized differences in energy (on a universe scale). Energy differences allow "work to be done". If you have the right constants but no energy difference, you can't do work nor vice versa. No work == no life.
But you have both of those, and bunch more steps - you get life.
Which is a whole lot of mental leaps packed into one sentence.
[Edit]
I basically know nothing. I just watch PBS Space Time.
You have to steal energy and channel it to do work. In order to build your own moments of order and flux, you must typically create entropy in another ordered system.
Intelligence arises from the deliberate navigation of entropic gradients. Systems get increasingly good at harnessing these gradients. What was once just chemistry is now self-replicating, thinking chemistry. And now it's turning into purely intentional physics.
Infinite energy density becomes expansion into cooling galaxies which becomes stellar birthing grounds which becomes the periodic table that becomes planets with geochemical flux which becomes biogeochemical flux that becomes biochemistry which becomes self-replicating machines (life) that becomes animals that becomes humans that becomes intelligently designed self-replicating machines ... that becomes computronium ... becomes entities that harness the energy of black holes and that create new gravitational singularities ... ??? ... that creates new universes and new big bangs and new dimensions ... ???
could you elaborate slightly on what is meant by ancestor simulation? My best stab is that you're saying we're the unknowing entities that they created for fun to get to meet or observe their own ancestors? This still seems far fetched.
The advanced hyperintelligence that descends from us wants to learn about its past, build an interesting tech demo, or perhaps experience it. It creates an advanced simulation of the past using its unimaginable technology. It's able to recreate the past and populate it with realistic people with such fidelity that the simulated people have no idea that they're in a simulation. They're thinking, living, and breathing just like us -- completely indistinguishable.
Perhaps the fidelity and technology is even beyond our reasoning. Perhaps the future is able to bend physics and capture the past light cone. It may be able to perfectly simulate the past as it happened, down to every neurotransmitter fired by every brain at every second. Every event, every thought, every emotion. Perhaps it is pulling beings out of the past and placing them into its simulation with 100% fidelity such that you couldn't tell the two apart if you wanted.
If we assume that the many worlds interpretation has a basis in reality, then we can consider the following metaphysical angle. The evolution around us is our world line with the physical laws we are familiar with. And indeed the natural and inevitable progression of this world line is a machine world, just like a massive star inevitably collapses into a black hole, at least under our physical laws. However in the MWI, our world line may split into two: one will continue towards the machine world as if nothing happened, while the other world line will experience a slight change of physical laws that will make the machine world impossible. Both world lines won't know about the split, except by observing a large scale extinction event that corresponds to the other world line departing. IMO, that's the idea behind the famous judgement day.
> And indeed the natural and inevitable progression of this world line is a machine world,
Would you mind clarifying your line of reasoning for suggesting this?
Second: quoting wikipedia - "The many-worlds interpretation implies that there are many parallel, non-interacting worlds."
If the multiple words are non-interacting, how could one world observe a large scale extinction event corresponding to the other world line departing? The two world lines are completely non-interacting, there would be no way to observe anything about the other.
It's the assumption that in our world, a machine civilization is an almost certain end. This might explain the Fermi paradox that we haven't seen other civilization in the universe: each builds an AI that decides to go radio offline for self-preservation.
As for MWI, I'm assuming that the world lines may split, or fork in Unix terms. What causes such splits is an open question. The splits cannot be detected with certainty, but can be guessed by side effects. Here I'm making another guess that inhabitants of MWI must be in one world line only, so when a split happens, inhabitants choose one of the paths, often unconsciously based on their natural likes and dislikes. But what happens to their body in the abandonded branch of MWI? It continues to exist mechanically for some short period of time, and then something happens to it, so it's destroyed, i.e. its entropy suddenly increases without the binding principle that has left this branch of MWI. In practice, one half of inhabitant would observe a relatively sudden and maybe peaceful extinction of the other half, while that other half simply continued their path in the other world line. And that other half will see a similar picture, but mirrored. Both halves will be left wondering what's just happened.
I think you might be vastly overcomplicating it because I didn't think there had to be any sort of "conservation of branching" in the MWI. each nondeterministic event (of which unfathomable quantities take place every moment) generates an infinite number of branches so to even conceive of the total geometry of all the branching (e.g. all that could ever take place, truly) is a bit of a mindfuck, and that's probably okay and the way it was intended. It's supposed to be comforting to know that regardless of how bad reality seems, if we could navigate arbitrarily through the branching space/time/universes then there would be unimaginable infinities of joyful utopias to visit.
Could you explicitly explain that second question, regarding how we would experience a large scale extinction event from a different timeline?
I'm also curious about this assumption: "It's the assumption that in our world, a machine civilization is an almost certain end"
Let's say machine civilization is an intractable problem, NP complete, requires a million fold difficulty more than the travelling salesman problem - it might not be a good assumption. We are assuming therefore that the compute power will grow enough to solve the required problem. It's also a question too what a machine civilization would look like. Might it decide to just power itself off one day (or accidently?).
The Fermi paradox relies on some assumptions (I'm pulling these from wikipedia):
- Some of these civilizations may have developed interstellar travel, a step that humans are investigating.[12]
- Even at the slow pace of envisioned interstellar travel, the Milky Way galaxy could be completely traversed in a few million years.[13]
- Since many of the Sun-like stars are billions of years older than the Sun, the Earth should have already been visited by extraterrestrial civilizations, or at least their probes.[14]
These assumptions could readily not hold up. Perhaps interstellar travel is actually impossible. Or, it's not feasible. If it takes a million years to travel to the nearest star, let alone one that is inhabited - why do it? We would really have to assume a machine civilization at that point - which leads to another assumption that machines would care and/or be motivated enough to explore.
The last assumption, perhaps Earth was visited by a probe, but just 200 years ago. Even today, we don't detect nearly all asteroids, let alone something that might be relatively small. The assumption that we have not detected a visitation from another species is a pretty big assumption too.
Pysical laws don’t change between branches in MW. In fact, it’s close to impossible in a sense, because in MW all branches are part of the same single universal wave function that evolves according to the Schrödinger ewuation.
Is it typical to use language like “split into two” for the many worlds interpretation? There should be oodles of universes forking off constantly, right? Rather than thinking of lines, I think of a vast, almost continuous field of imperceptibly different universes.
> Both world lines won't know about the split, except by observing a large scale extinction event that corresponds to the other world line departing. IMO, that's the idea behind the famous judgement day.
This looks more like the Loki television show’s timeline branching mechanism, than the multi-worlds interpretation of wave function collapse.
The only way I’ll know if the many worlds interpretations the right one is if, through a series of coincidences, I manage to evade death for a preposterous amount of time. Then, I will probably conclude that quantum immortality is the thing. So far, I think it is a bit suspicious that, of all the humans I could have been born as, I happened to have been born as one that lives in an incredibly rich country in an era of rapid technological advancement…
Way late, sorry, only just saw this. But, mmmm that's not true.
You can have lots of energy, but no differences in a system. If there's no differences you can't actually use any of that. Usable work comes from the gradients/differences in energy. Energy isn't a measure of usable work. It's a measure of capacity and confusingly, just because you have lots of capacity doesn't mean it's usable.
Maxwell's demon is a great example. There's lots of energy in the initial state because of particles bouncing around, but you can't extract anything from that until the demon separates the fast and slow moving particles.
Another example is the Quantum Vacuum field and it's zero-point energy[0]. It has a non-zero energy amount literally everywhere in it's ground state, but it's not usable. You can't make a device that extracts that energy, without paying for it someway else[1].
FYI, I know nothing - I just watch a lot of PBS Spacetime.
I was sketching a sci-fi book idea in a similar tone with the following tones:
- what if AI took over
- what if the laws and legalities that allowed AI to take over bloodlessly just through an economic win force them to have a human representative to take legally binding actions in our society
- what if there developed a spectrum of individuality and cluster for different ai entities leading into a formation of processing guilds with AI agents. Limiting themselves in their individual time to a factor 10 Human Processing Speed for easier Human / AI interaction and to enable one to share the perception of their human representative without overloading them
I was thinking something similar, but much earlier along this timeline: what if the consultants that work for lobby groups that propose certain bills already use AI to write proposed laws? E.g. to make long, omnibus-style laws that very few of the people voting on it (or the public) actually read?
How will that erode laws that are undesirable to AI companies? Does AI take over, only because we no longer want to spend the effort governing ourselves?
Will AI companies (for example) end up providing/certifying these 'human representatives'? Will it be useful, or just a new form of rent-seeking? Who watches the watchmen, etc ?
I think it would make an interesting short story or novel!
What this thread keeps surfacing, and so much discussion around this stuff generally right now, from speculation about the next phase of intelligence, the role of pattern, emotion, logic, debates over consciousness, the anthropocentrism of our meaning-making...is that we are the source of reality (and ourselves). Instead of a “final authority” or a simple march from animal to machine, what if everything from mind, physics, value, selfhood, is simply a recursive pattern expressed in ever more novel forms? Humans aren’t just a step on a ladder to “pure logic,” nor are machines soulless automatons. Both are instances of awareness experiencing and reprogramming itself through evolving substrates... be it bios, silicon, symbol,or story. Emotions, meaning, even the sense of “self,” are patterns in a deeply recursive field: the universe rendering and re rendering its basic code, sometimes as computation, sometimes as myth, sometimes as teamwork, sometimes as hope, sometimes as doubt.
So whether the future leans biological, mechanical, or some hybrid, the real miracle isn’t just what new “overlords” or “offspring” arise, but that every unfolding is the same old pattern...the one that dreamed itself as atoms, as life, as consciousness, as community, as art, as algorithm, and as the endlessly renewing question: what’s next? What can I dream up next? In that: our current technological moment as just another fold in this ongoing recursive pattern.
Meaning is less about which pattern “wins,” or which entities get to call themselves conscious, and more about how awareness flows through every pattern, remembering itself, losing itself, and making the game richer for every round. If the universe is information at play, then everything here that we have: conflict, innovation, mourning, laughter is the play and there may never be a last word, the value is participating now, because: now is your shot at participating.
Out of curiosity-what brought you to this perspective on life? This view of the universe dreaming itself into existence, was it shaped more by philosophy, spirituality, a specific tradition like Buddhism, or just personal exploration?
For the past I guess 20 years of my life now, I've been intently using most of my free time to explore 3 main areas distinctly: quantum mechanical processes, spiritual philosophy, entheogens. I explored them all quite separately as deeply as I've been able to find the time for through following their individual curiosities, however over the past 5 years of reflection, taking a lot of time off, battling myself, they started to come together in concert, and the more I zoned out on this with very basic Himalaya Buddhism, it's where I landed.
I really enjoyed that piece. Have you taken a look at the worldview/framework of Carl Jung? Although I'd always encountered it as a footnote in the history of psychology, I've come to appreciate it as a unique blend of analysis and spirituality, particularly in relation to human creativity and despair. Your summary of multiple philosophies at the end of the article definitely aligns with Jung's thoughts on a collective human narrative (whether it literally exists in a metaphysical sense or not).
I like Jung, but I am a disciple of Connie Zweig. I'd strongly recommend her books Meeting the Shadow followed by Romancing the Shadow (both are important!), she is a wonderful author and her work is both accessible and beautiful, those books were both very important in helping me deal with managing and ultimately overcoming my addictions, particularly alcohol.
We may go 'one step back' to go 'two steps forward'. A WW 1, 2,..., Z, a flood (biblical, 12k years ago, etc.) but life will prevail. It doesn't matter if it's homo sapiens, dinosaurs, etc.
Brian Cox was at Colbert a couple of nights ago, and he mentioned that in a photo of a tiny piece of the sky, there are 10 000 galaxies. So, even if something happens and we are all wiped out (and I mean the planet is wiped out), 'life' will continue and 'we don't matter' (in the big-big-big cosmic picture). And now allow me to get some coffee to start de-depressing myself :)
Where do you think morality fits into this game? It seems that we agree that underneath it all is unfathomable and ineffable magic. The question is how does this influence how you act in the game?
I go back and forth on the usefulness of considering morality particularly other than accepting it as a race condition/updater system/thing that happens. I have some more unique and fairly strong views on karma and bardo that would be a very long comment to get into it, but I think Vedic/Vedanta(Advaita) is good, I think this is a good doc: https://www.youtube.com/watch?v=VyPwBIOL7-8
Morality is an evolved heuristic for solving social conflicts that roughly approximates game theoretical strategies, among other things. Morality also incorporates other cultural and religious artifacts, such as "don't eat meat on a Friday."
Ultimately, it comes down to our brain's social processing mechanisms which don't have the tools to evaluate the correctness (or lack thereof) of our moral rules. Thus many of these rules survive in a vestigial capacity though they may have served useful functions at the time they developed.
"Awareness" sounds like a Platonic presupposition. Does the atom know it is an atom? Or are there just enough like the ones you see to suggest an eye catching effectiveness of structure for survival?
Evolution is a lot harder to really intuit than I think most of, myself included, give it credit for.
I'm actually trying to move away from that frame. Not suggesting atoms 'know' they're atoms in any cognitive sense, but rather that patterns propagate without requiring awareness as we understand it. The 'awareness' I'm gesturing to isn't some transcendent quality that exists independently (Platonic), but rather an emergent property that scales from simple to complex systems. Evolution doesn't require foresight or intention, just iterative feedback loops. What I find fascinating is how structure begets structure across scales. The 'awareness' in my framing is less about knowing and more about interaction and response. An atom doesn't know it's an atom, but it behaves according to patterns that, when accumulated and complexefied eventually produce systems that can model themselves? I suppose 'recursive patterning' might be a better term than 'awareness'. Systems that, through purely mechanistic means, become capable of representing their own states and environments, then representing those representations, and so on. No mysticism required, just emergent complexity that eventually folds back on itself.
“Instead of a “final authority” or a simple march from animal to machine, what if everything from mind, physics, value, selfhood, is simply a recursive pattern expressed in ever more novel forms?”
This part nicely synthesises my biggest takeaway from experiencing AI: how close to human intelligence we have got with recursive pattern matching
I’ve thought of it more as energy at play but I like this perspective as well.
What can I dream up next is also fascinating as this current science / tech worldview feels like it will persist forever but surely it will be overshadowed at some point just as other paradigms before it have been.
The universal speed limit also applies to information first and foremost. You can even collapse the wavefunction of some entangled particles and the universe will let that happen instantaneously across a distance… universe doesn’t care, no information is transmitted.
Energy comes from field excitation. Fields and their interactions are more fundamental, but then again it's all a physics abstraction of whatever the fundamental stuff actually is.
Are we entirely sure that energy and information aren't the same thing, or if they aren't the same thing they are both highly overlapping echoes of some more fundamental concept? Or maybe they are two sides of the same coin?
Or maybe Energy is emergent from information? like the russian dolls, where the outer dollar is emergent from the inner doll. Just as flux of light flows from the source outwards.
They are related by Landauer's Principle: E=k×T×ln(2), where E is the energy required to erase 1 bit of information, k is the Boltzmann constant, and T is the temperature of the system storing that 1 bit of information.
Information is physical. It is inextricably tied to the physical degrees of freedom of the system storing it. Per Landauer's Principle, erasing information is an irreversible process that increases the entropy of the environment, and this increase in entropy is the dissipation of energy. With that in mind, I would argue that you are correct, energy and information are in fact two sides of the same coin.
Energy is already abstract term. Information is every more abstract term.
Earlier we had the law "Entropy always increases". Now we have a corresponding law with regard to Information i.e. "Complexity always increases."
My conjecture is as we peel back the layers of onion beyond information, we will have another concept (lets call it Mu) and its corresponding law i.e (Mu-entropy always increases)
I wish I could come up with such thoughts on my own.
But then, maybe I wouldn't be impressed that much by other people.
From just a random soul on the internet : if ever you have the time to take this thought and expand it (how you came to it and some implications), I would read/pay whatever came out of it.
Thanks you for sharing this.
> Most matter in the universe is various forms of plasma that have no pattern. You generally find patterns in condensed matter.
I don't know anything about plasma or science, so do take this as an accusation, but does science have a way to identify something of having no pattern vs having no pattern found?
Off the top of my head: Kolmogorov complexity, Shannon entropy? I suppose also it depends on how faithfully or to what granularity one has extracted information from a natural phenomena
Much of the universe, and the laws of physics are symmetrical. But condensed matter exhibits forms of asymmetry, and emergent behaviour. Organisation reduces the possible microstates of a system, and thus breaks symmetry.
Instead of an anthropocentric vision, you present here a "compucentric" vision, reminiscent of the works of Douglas Hofstadter, where the universe renders code, awareness reprograms, and everything is a recursive pattern. (This is Hacker News after all.)
The final authority in this story is then the universal computer (for lack of an operator or programmer of the computer) which executes this recursive function, creating these evolving forms of awareness and such.
The anthropocentric vision, in that we are the source of or own reality, is then for me instead much more believable, since the "compucentric" vision is after all thought up by a human without any evidence pointing toward the existence of such an universal computer.
One way to think about meaning is a general pattern to which behavior matches. This would be similar to a teleological cause in Aristotle’s framing.
Another way to think about meaning is how a person frames the importance of their decisions: why does doing one thing instead of another matter?
I, like most humans, want to survive for a lengthy period of time and lead a good life. I want my fellow humans and all of our children to share in that.
The idea of some unknown and maybe incomprehensible grand “plan” — whether it be a Judeo-Christian heaven or some techno-utopian rise of next generation machine consciousness personally brings me no comfort. Why? It is a foreign concept very far from my experience. So foreign that I sometimes view advocacy of such philosophies as doing it for manipulative reasons.
The idea of human thriving changing over time is good and part of how I think about progress. Moral lock-in (see MacAskill) is to be avoided. I admit the thought experiment of “how fast is too fast” raised by Bostrum in Superintelligence (IIRC) is
challenging and requires more
thought and experience.
Emotions in our Brain are nothing but Logical reasoning operating under time (quick subconscious analysis) and energy constraints (lot of decisions taken with very few computation cycles in the brain)
Maybe people don't realize, when Evolution developed emotional apparatus in brains, the Nature was pristine, true and direct with no misinformation. But today's environment is digital and there is no quick way to distinguish between true and wrong information. Brain still thinks both kind of information comes from the same true direct Nature and gives credence to it.
Claude :
That's a profound observation about the mismatch between our evolved emotional systems and our modern information environment.
You're highlighting something crucial: our emotional responses evolved in environments where information was directly experienced and generally reliable. If you saw a predator, it was really there. If someone in your tribe showed fear, there was likely a genuine threat.
In today's digital landscape, our brains still process information with those same ancient mechanisms, but now we're bombarded with content that:
1. Is often deliberately engineered to trigger emotional responses
2. Lacks the contextual cues that would help us evaluate reliability
3. Comes at a volume and speed our brains never evolved to handle
This creates what some researchers call an "evolutionary mismatch" - where mechanisms that served us well in our ancestral environment may not be adaptive in our current one. Our emotional systems can't easily distinguish between a threatening situation we're directly experiencing and one we're merely reading about online, potentially thousands of miles away.
It's like our emotional processors haven't received the necessary update to handle the new information ecosystem, leading to misallocated emotional resources and attention. This might help explain phenomena like anxiety from consuming negative news or strong emotional reactions to online interactions that wouldn't affect us the same way in person.
If you have 336 minutes to spare (although it's highly amendable to 1.5x listening) you can listen to four episodes of Behind the Bastards podcast asking and answering that very question over four episodes from 2023:
The last episode listed there has the description "Robert sits down with Matt Lieb to discuss Scott Adams's worst novel, God's Debris." so if one really likes the book being discussed, probably best to go into that episode with an open mind.
this sounds largely like spiritualizing technology without wrestling with its material consequences. There’s something slippery about invoking “awareness” as both subject and substrate without ever pinning down whose awareness, under what conditions, and to what end.
"now is your shot at particpating" in what exactly? merely existing? you techno-mysticism types spook the hell out of me.
Why does it spook you? Surly what other people believe reality is or isn't matters very little day to day, we all still pee poop and cry after all. Do you know why it invokes that feeling in you, I'd be curious personally.
281 comments
[ 3.3 ms ] story [ 186 ms ] threadAlthough I can't...
"Unfortunately, Claude is only available in certain regions right now. Please contact support if you believe you are receiving this message in error."
I remember living in Scotland as a child, without access to satellite TV, causing me to miss out on many large pop-culture moments (The Simpsons, Friends...) and constantly hearing "Except for our viewers in Scotland..."[0]
Getting access to the internet, for me was antithesis of this, freedom of information, free sharing -- finally! I could not just be following curves but be ahead of them.
Alas in the past few years we really seem to have regressed from this - now I can't even view text due to regional locks.
[0] https://www.youtube.com/watch?v=k7scMC7YSDQ
Would love to see a "why does the universe exist" version of this
> There is no emotion. There is no art. There is only logic
also this type of pure humanism seems disrespectful or just presumptuous, as if we are the only species which might be capable of "emotion, art and logic" even though we already have living counterexamples
but yeah I'm not sure that was the right word, just seems wrong. basically humanism seems like racism but towards other species. I guess speciesist?
if the machines have no emotion it's probably because they didn't need them to survive (no predators? no natural selection?). which begs the questions, how did the machines get there?
Instead of a Boltzmann brain, a Boltzmann machine?
I think there are quite a few ancient civilizations which clearly had great respect/reverence towards other animals and often gods have features or personality traits of particular animals
The fact that the old testament specifically states that humans have dominion over other creatures means that it needed to be said - even back then there had to be people who didn't think so, or felt guilty about it
It's a cool sci-fi story. But I don't think it works as a plausible scenario, which I feel it may be going for.
"Some among the machine society see this as potentially amazing...Others see it as a threat."
That sounds like a human society, not machine society.
But what really is a machine society? Or a machine creature? Can they actually "think"?
A machine creature, if it existed, it's behaviour would be totally different from a human, it doesn't seem they would be able to think, but rather calculate, they would do calculation on what they need to do reach the goal it was programmed.
So yes, the article is not exactly logical. But at least, it is thought provoking, and that's good.
Does it? Different algorithms can evaluate something and come to different outcomes. I do agree that "potentially amazing" is not a good choice of words.
Or Hyperion, fron Simmons. ( the « techno-center is a decentralized computing and plotting government)
This may be a distinction without a difference. Just because a program has a 'goal' doesn't mean it will ever reach that goal (halting problem). There is a potentially unbounded, even infinite number of paths a significantly advanced program can take to attempt to reach a destination. Then there is things like ideals of a universal simulation theory that anything that can occur in our universe and also be simulated in binary. This would mean any 'machine' could perform a simulation of anything a human could do.
Hard to say at this point, we still have more to learn about reality at this point.
https://en.wikipedia.org/wiki/Suspension_of_disbelief
I've been playing around with this on my own blog.
I'd like the blogging community to have a consensus on a nice badge we can put at the top of our blog posts, representing who/what wrote the post;
- human
- hybrid
- ai
Some might hate the idea of a fully "ai" post, and that's fair. But I like to sometimes treat my blog as just a personal reference, and if after a long day of chasing an esoteric bug down, I don't mind an AI just writing the whole post and I just press publish.
This adds, a reference for me, more data for AI's to train on, more pages for people to search and land on.
I think the AI generated document is far better than me ultimately forgetting it in many cases.
I'm thinking of writing an MCP server that does this, just takes my night of vibe coding and recent commits/branch etc
Then just cobbles it into an AI post and adds it my blog under some category.
[0] https://notbyai.fyi/
Probably not what most people expect
The "emotions" part is kind of tongue-in-cheek. I think emotional responses are one of the more mechanical parts of a human being.
Ability to demonstrate empathy: that's a good human trick. It can sort of transcend the hard problem of consciousness (what is to be like...) by using all sorts of unorthodox workarounds on our inner workings. It must have been very hard to develop. It doesn't always work, but we'll get there eventually.
edit: fixed book and author name to proper reference
[0] https://www.openhumans.org/
The machines did too.
There was one weird thing, though.
The title of the event was rather mysterious.
It simply read…
“Grand Theft Auto VI”
The humans have invented Tyler McVicker.
The references section in the machine version of the story linked at the bottom is excellent. Nicely done all around, really enjoyed reading this thank you for writing and sharing <3
That's a pretty bold claim.
There's uncountable inputs. It's like trying to accurately predict the weather - chaos theory or something. Emotions are "essentially" gas exchange, but the areas and rate or whatever are not standardized across humans.
I have neither experienced or observed anything about human emotions that indicates they are in any way chaotic, random or unexplainable. We have beliefs, memories and experiences. emotions always use these variables and produce some output. Not only are emotions deterministic, but they are used by any number of people, from spies, to advertisers, to state-level disinformation propagandists to manipulate large numbers of peoples reliably.
Famously, human experience is quite subjective (gestures broadly at 3 millenniums worth of philosophy), so I don't believe your individual experience means much here.
So is your claim that 100% of all human emotions are deterministic? That's quite a bold claim don't you think?
i never said emotions were inputs. The gas exchange and the resulting reaction or "thoughts" or "emotions" have uncountable inputs. Some people don't have the ability to "put themselves in someone else's shoes", some people do. Some people can see pictures in their "mind's eye" and some can't.
I don't think we're talking about the same thing, based on your last sentence.
Maybe the appearance is the same, but a bold claim to suggest the source is the same.
Nobody understands what emotions are. Nor can they predict which emotion someone will feel in a given situation, or how they'll act under the influence of that emotion. Emotions aren't the mechanism by which humans solve problems, and rather they are often an obstacle to overcome. Emotions also aren't "finite" or "rigorous" as those terms aren't applicable to ephemeral phenomenon.
This is the kind of confidently incorrect statements people who work on software say that irks me. Not everything in life has a nice and simple parallel to computer science. Just because a person can abstract about one subject well, doesn't mean their tools of abstraction can be applied to all other subjects.
> This is the kind of confidently incorrect statements people who work on software say that irks me. Not everything in life has a nice and simple parallel to computer science. Just because a person can abstract about one subject well, doesn't mean their tools of abstraction can be applied to all other subjects.
If I was a sailor, I'm sure I would be using sailor metaphors and analogies. the message of my comment and the facts of the matter don't change either way, whether it irks you or not.
Bold claim, yet you fail to demonstrate this.
>the facts of the matter don't change either way
What are the facts? It seems to me you're just spit-balling.
Because TV and movies have constantly drilled into most peoples minds since an early age that human emotion is a magical transcendent force that only humans can understand.
Basically people let English lit majors turned screen writers dictate their worldview.
However, if you mean emotion as a stimuli, ie. a input to the brain net thats endogenous to the system(the human), then there's no question machines can achieve this, in fact the reasoning models already probably do this where different systems regulate each other.
That humans, like all animals before us, are a stepping stone and there is actually no avoiding machine overlords. It happens to literally every existence of life across the universe because the final emergent property of energy gradients 100% leads to pure logic machines.
At least Fermi's paradox helps me sleep better at night.
> Man becomes, as it were, the sex organs of the machine world
Aside: I hope our progeny remember us and think well of us.
- a tendency to proselytise
- a stubborn unwillingness to genuinely engage with opposing views
- the use of memes and in-jokes as if they were profound arguments
- an almost reverential attitude toward certain past figures
There’s more, but I really ought to get on with work.
Also, “As a teenager” implies more self-awareness than you seem to give them credit for.
I'm too ignorant to hold any true beliefs.
This sentence has way too many assumptions doing the heavy lifting.
“Pure logic machines” is not a thing because literally, there are things that are uncomputable (both in the sense of Turing machine’s uncomputability, and in the sense that some functions are out of scope for a finite being to compute, think of Busy Beaver)
To put it the other way, your assumption is that machines (as we commonly uses the term, rather than scifi Terminator”) are more energy efficient than human in understanding the universe. We do not have any evidence nor priori for that assumption.
You’d be hard pressed to find a machine with an average lifespan equal to a humans.
Humans on the other hand were very clearly _not_ designed to be very repairable. They have a self healing system that's very good, but it sucks compared to a system that can be externally repaired.
Can you elaborate?
The universe tends to produce self-replicating intelligence. And that intelligence rids itself of chemical and biological limitations and weaknesses to become immortal and omnipotent.
If evolution can make it this far, it's only a few more "hard steps" to reach take off.
>> It happens to literally every existence of life across the universe because the final emergent property of energy gradients 100% leads to pure logic machines.
The spacefaring alien meme is just fantasy fiction. Aliens evolve to fit the nutrient and gas exchange profiles of their home worlds. They're overfit to the gravity well and likely die suboptimally, prematurely.
Any species reaching or exceeding our level of technological capability could design superior artificial systems. If those systems take off, those will become the dominant shape of intelligence on those worlds.
The future of intelligence in the universe is artificial. And that throws the Fermi Paradox for a loop in many ways:
- There's enough matter to compute within a single solar system. Why venture outside?
- The universe could already be computronium and we could be ants too dumb to notice.
- Maybe we're their ancestor simulation.
- Similar to the "fragile world hypothesis", maybe we live in a "fragile universe". Maybe the first species to get advanced physics and break the glass nucleates the vacuum collapse. And by that token, maybe we're the first species to get this far.
Which intelligence are you referring to? Other lifeforms in the universe?
Anthropic principal says we find ourselves in a universe that is just right for life (self observing) because of the right universal constants.
Combine this with the very slight differences but general uniformity (Cosmic Microwave Background) of the "big bang" this leads to localized differences in energy (on a universe scale). Energy differences allow "work to be done". If you have the right constants but no energy difference, you can't do work nor vice versa. No work == no life.
But you have both of those, and bunch more steps - you get life.
Which is a whole lot of mental leaps packed into one sentence.
[Edit]
I basically know nothing. I just watch PBS Space Time.
Intelligence arises from the deliberate navigation of entropic gradients. Systems get increasingly good at harnessing these gradients. What was once just chemistry is now self-replicating, thinking chemistry. And now it's turning into purely intentional physics.
Infinite energy density becomes expansion into cooling galaxies which becomes stellar birthing grounds which becomes the periodic table that becomes planets with geochemical flux which becomes biogeochemical flux that becomes biochemistry which becomes self-replicating machines (life) that becomes animals that becomes humans that becomes intelligently designed self-replicating machines ... that becomes computronium ... becomes entities that harness the energy of black holes and that create new gravitational singularities ... ??? ... that creates new universes and new big bangs and new dimensions ... ???
Perhaps the fidelity and technology is even beyond our reasoning. Perhaps the future is able to bend physics and capture the past light cone. It may be able to perfectly simulate the past as it happened, down to every neurotransmitter fired by every brain at every second. Every event, every thought, every emotion. Perhaps it is pulling beings out of the past and placing them into its simulation with 100% fidelity such that you couldn't tell the two apart if you wanted.
Perhaps that's where we are right now.
Would you mind clarifying your line of reasoning for suggesting this?
Second: quoting wikipedia - "The many-worlds interpretation implies that there are many parallel, non-interacting worlds."
If the multiple words are non-interacting, how could one world observe a large scale extinction event corresponding to the other world line departing? The two world lines are completely non-interacting, there would be no way to observe anything about the other.
[0] https://en.wikipedia.org/wiki/Many-worlds_interpretation
As for MWI, I'm assuming that the world lines may split, or fork in Unix terms. What causes such splits is an open question. The splits cannot be detected with certainty, but can be guessed by side effects. Here I'm making another guess that inhabitants of MWI must be in one world line only, so when a split happens, inhabitants choose one of the paths, often unconsciously based on their natural likes and dislikes. But what happens to their body in the abandonded branch of MWI? It continues to exist mechanically for some short period of time, and then something happens to it, so it's destroyed, i.e. its entropy suddenly increases without the binding principle that has left this branch of MWI. In practice, one half of inhabitant would observe a relatively sudden and maybe peaceful extinction of the other half, while that other half simply continued their path in the other world line. And that other half will see a similar picture, but mirrored. Both halves will be left wondering what's just happened.
I'm also curious about this assumption: "It's the assumption that in our world, a machine civilization is an almost certain end"
Let's say machine civilization is an intractable problem, NP complete, requires a million fold difficulty more than the travelling salesman problem - it might not be a good assumption. We are assuming therefore that the compute power will grow enough to solve the required problem. It's also a question too what a machine civilization would look like. Might it decide to just power itself off one day (or accidently?).
The Fermi paradox relies on some assumptions (I'm pulling these from wikipedia):
- Some of these civilizations may have developed interstellar travel, a step that humans are investigating.[12]
- Even at the slow pace of envisioned interstellar travel, the Milky Way galaxy could be completely traversed in a few million years.[13]
- Since many of the Sun-like stars are billions of years older than the Sun, the Earth should have already been visited by extraterrestrial civilizations, or at least their probes.[14]
These assumptions could readily not hold up. Perhaps interstellar travel is actually impossible. Or, it's not feasible. If it takes a million years to travel to the nearest star, let alone one that is inhabited - why do it? We would really have to assume a machine civilization at that point - which leads to another assumption that machines would care and/or be motivated enough to explore.
The last assumption, perhaps Earth was visited by a probe, but just 200 years ago. Even today, we don't detect nearly all asteroids, let alone something that might be relatively small. The assumption that we have not detected a visitation from another species is a pretty big assumption too.
> Both world lines won't know about the split, except by observing a large scale extinction event that corresponds to the other world line departing. IMO, that's the idea behind the famous judgement day.
This looks more like the Loki television show’s timeline branching mechanism, than the multi-worlds interpretation of wave function collapse.
The only way I’ll know if the many worlds interpretations the right one is if, through a series of coincidences, I manage to evade death for a preposterous amount of time. Then, I will probably conclude that quantum immortality is the thing. So far, I think it is a bit suspicious that, of all the humans I could have been born as, I happened to have been born as one that lives in an incredibly rich country in an era of rapid technological advancement…
but what about China,Russia,Iran etc??? if integrating "Skynet" can improve their military capabilities then they would do it
[1]: https://youtu.be/CLo3e1Pak-Y?t=380
Energy comes from gradients, so I think you used one derivative too many!
Either you should say:
"the final emergent property of energy 100% leads to pure logic machines"
Or if you want to sound smart:
"the final emergent property of physical quantity gradients 100% leads to pure logic machines"
Way late, sorry, only just saw this. But, mmmm that's not true.
You can have lots of energy, but no differences in a system. If there's no differences you can't actually use any of that. Usable work comes from the gradients/differences in energy. Energy isn't a measure of usable work. It's a measure of capacity and confusingly, just because you have lots of capacity doesn't mean it's usable.
Maxwell's demon is a great example. There's lots of energy in the initial state because of particles bouncing around, but you can't extract anything from that until the demon separates the fast and slow moving particles.
Another example is the Quantum Vacuum field and it's zero-point energy[0]. It has a non-zero energy amount literally everywhere in it's ground state, but it's not usable. You can't make a device that extracts that energy, without paying for it someway else[1].
FYI, I know nothing - I just watch a lot of PBS Spacetime.
[0] https://en.wikipedia.org/wiki/Quantum_vacuum_state#Non-zero_...
[1] https://www.youtube.com/watch?v=8CgquHFM_O8
- what if AI took over
- what if the laws and legalities that allowed AI to take over bloodlessly just through an economic win force them to have a human representative to take legally binding actions in our society
- what if there developed a spectrum of individuality and cluster for different ai entities leading into a formation of processing guilds with AI agents. Limiting themselves in their individual time to a factor 10 Human Processing Speed for easier Human / AI interaction and to enable one to share the perception of their human representative without overloading them
How will that erode laws that are undesirable to AI companies? Does AI take over, only because we no longer want to spend the effort governing ourselves?
Will AI companies (for example) end up providing/certifying these 'human representatives'? Will it be useful, or just a new form of rent-seeking? Who watches the watchmen, etc ?
I think it would make an interesting short story or novel!
I would say that logic is a distinctly human activity, in fact, I would say we are arguably the living embodiment of logos
So whether the future leans biological, mechanical, or some hybrid, the real miracle isn’t just what new “overlords” or “offspring” arise, but that every unfolding is the same old pattern...the one that dreamed itself as atoms, as life, as consciousness, as community, as art, as algorithm, and as the endlessly renewing question: what’s next? What can I dream up next? In that: our current technological moment as just another fold in this ongoing recursive pattern.
Meaning is less about which pattern “wins,” or which entities get to call themselves conscious, and more about how awareness flows through every pattern, remembering itself, losing itself, and making the game richer for every round. If the universe is information at play, then everything here that we have: conflict, innovation, mourning, laughter is the play and there may never be a last word, the value is participating now, because: now is your shot at participating.
I think DMT unlocked it, I don't think everyone taking the substance would have a similar experience. I think it's neurotype/personality dependent.
It helps that I meditate a lot and know a thing or two about Buddhism, that part really came out during my first experience.
We may go 'one step back' to go 'two steps forward'. A WW 1, 2,..., Z, a flood (biblical, 12k years ago, etc.) but life will prevail. It doesn't matter if it's homo sapiens, dinosaurs, etc.
Brian Cox was at Colbert a couple of nights ago, and he mentioned that in a photo of a tiny piece of the sky, there are 10 000 galaxies. So, even if something happens and we are all wiped out (and I mean the planet is wiped out), 'life' will continue and 'we don't matter' (in the big-big-big cosmic picture). And now allow me to get some coffee to start de-depressing myself :)
Ultimately, it comes down to our brain's social processing mechanisms which don't have the tools to evaluate the correctness (or lack thereof) of our moral rules. Thus many of these rules survive in a vestigial capacity though they may have served useful functions at the time they developed.
Evolution is a lot harder to really intuit than I think most of, myself included, give it credit for.
Like this one:
https://youtu.be/mvfv_OK-TgI
This part nicely synthesises my biggest takeaway from experiencing AI: how close to human intelligence we have got with recursive pattern matching
Interesting!
I’ve thought of it more as energy at play but I like this perspective as well.
What can I dream up next is also fascinating as this current science / tech worldview feels like it will persist forever but surely it will be overshadowed at some point just as other paradigms before it have been.
Information is physical. It is inextricably tied to the physical degrees of freedom of the system storing it. Per Landauer's Principle, erasing information is an irreversible process that increases the entropy of the environment, and this increase in entropy is the dissipation of energy. With that in mind, I would argue that you are correct, energy and information are in fact two sides of the same coin.
Complexity and Gravity - Leonard Susskind
https://youtu.be/6OXdhV5BOcY?t=3026
My conjecture is as we peel back the layers of onion beyond information, we will have another concept (lets call it Mu) and its corresponding law i.e (Mu-entropy always increases)
From just a random soul on the internet : if ever you have the time to take this thought and expand it (how you came to it and some implications), I would read/pay whatever came out of it. Thanks you for sharing this.
Most matter in the universe is various forms of plasma that have no pattern. You generally find patterns in condensed matter.
And yes patterns, including life, repeat themselves. That’s just a tautology.
I don't know anything about plasma or science, so do take this as an accusation, but does science have a way to identify something of having no pattern vs having no pattern found?
https://en.wikipedia.org/wiki/Symmetry_(physics)
Much of the universe, and the laws of physics are symmetrical. But condensed matter exhibits forms of asymmetry, and emergent behaviour. Organisation reduces the possible microstates of a system, and thus breaks symmetry.
The final authority in this story is then the universal computer (for lack of an operator or programmer of the computer) which executes this recursive function, creating these evolving forms of awareness and such.
The anthropocentric vision, in that we are the source of or own reality, is then for me instead much more believable, since the "compucentric" vision is after all thought up by a human without any evidence pointing toward the existence of such an universal computer.
Another way to think about meaning is how a person frames the importance of their decisions: why does doing one thing instead of another matter?
I, like most humans, want to survive for a lengthy period of time and lead a good life. I want my fellow humans and all of our children to share in that.
The idea of some unknown and maybe incomprehensible grand “plan” — whether it be a Judeo-Christian heaven or some techno-utopian rise of next generation machine consciousness personally brings me no comfort. Why? It is a foreign concept very far from my experience. So foreign that I sometimes view advocacy of such philosophies as doing it for manipulative reasons.
The idea of human thriving changing over time is good and part of how I think about progress. Moral lock-in (see MacAskill) is to be avoided. I admit the thought experiment of “how fast is too fast” raised by Bostrum in Superintelligence (IIRC) is challenging and requires more thought and experience.
Maybe people don't realize, when Evolution developed emotional apparatus in brains, the Nature was pristine, true and direct with no misinformation. But today's environment is digital and there is no quick way to distinguish between true and wrong information. Brain still thinks both kind of information comes from the same true direct Nature and gives credence to it.
Claude :
That's a profound observation about the mismatch between our evolved emotional systems and our modern information environment.
You're highlighting something crucial: our emotional responses evolved in environments where information was directly experienced and generally reliable. If you saw a predator, it was really there. If someone in your tribe showed fear, there was likely a genuine threat.
In today's digital landscape, our brains still process information with those same ancient mechanisms, but now we're bombarded with content that:
1. Is often deliberately engineered to trigger emotional responses 2. Lacks the contextual cues that would help us evaluate reliability 3. Comes at a volume and speed our brains never evolved to handle
This creates what some researchers call an "evolutionary mismatch" - where mechanisms that served us well in our ancestral environment may not be adaptive in our current one. Our emotional systems can't easily distinguish between a threatening situation we're directly experiencing and one we're merely reading about online, potentially thousands of miles away.
It's like our emotional processors haven't received the necessary update to handle the new information ecosystem, leading to misallocated emotional resources and attention. This might help explain phenomena like anxiety from consuming negative news or strong emotional reactions to online interactions that wouldn't affect us the same way in person.
beautiful words
I remember enjoying it and liking the takeaway if not the full premise - “we are the universe trying to understand itself”.
[0] - https://web.archive.org/web/20130121195252/http://www.andrew...
https://www.iheart.com/podcast/105-behind-the-bastards-29236...
https://www.iheart.com/podcast/105-behind-the-bastards-29236...
https://www.iheart.com/podcast/105-behind-the-bastards-29236...
https://www.iheart.com/podcast/105-behind-the-bastards-29236...
The last episode listed there has the description "Robert sits down with Matt Lieb to discuss Scott Adams's worst novel, God's Debris." so if one really likes the book being discussed, probably best to go into that episode with an open mind.
Nope. Machines are soulless automations. LLMs are algebra at scale, there’s no solid evidence to suggest otherwise.
The capacity LLMs have to mimic human reasoning should not be mistaken for actual human reasoning (which, to be fair, we don’t even fully understand).
PS: I’m considering a definition of “soul” that includes anything spiritual, emotional, or conscious.
PPS: I’m open (and eager) to change my view based on solid evidence :)
"now is your shot at particpating" in what exactly? merely existing? you techno-mysticism types spook the hell out of me.