
r/IsaacArthur

Orvital rings around gas giants
Orbital rings have been described as making platforms over planets or other massive objects that normally don't have solid surfaces (gas giants, stars, black holes), or surfaces that can't otherwise be accessed. How then would you anchor them in place over the planet to keep them from precessing, or otherwise drifting off course?
Anyone interested in helping make a video about actually designing a Topopolis?
So I've had this idea bouncing around in my head for a bit and I think I actually want to try and make something out of it.
I want to make a YouTube series tentatively called "So You Wanna Make a Topopolis?"
The basic idea is instead of just making another video explaining what a Topopolis is, I want to treat it like we're actually trying to build one. Start with the basic concept, work through the problems one at a time, and slowly end up with our own reasonably thought-out design.
I've already started putting together the overall project and how the series would work, but realistically I know my limitations lol. I can do the research and I can learn things as I go, but I am not a physicist, 3D animator, professional editor, etc. And I think this would be WAY cooler as something a few people made together anyway.
So I'm curious if anybody here would be interested in helping make the first video.
Could be research, physics/engineering knowledge, Blender/animation, editing, graphics, or just someone who's really into megastructures and wants to contribute ideas.
For now I literally just want to get one good pilot made. If it turns into something people actually like, then we can figure out where to go from there and potentially crowdfund the rest of the project.
I'm not expecting anybody to suddenly dedicate the next year of their life to my random YouTube idea lol. Mostly I'm throwing this out there to see if there are a few people who think this sounds cool and might want to help me actually make it.
Dm please!
Are lithium‑fed MPD thrusters the most promising near-term option for interplanetary travel?
It seems NASA is going all in on development of magnetoplasmadynamic thrusters since they really want the high efficiency of NEP with as high a thrust it can manage with that setup. So MPD seems the best option given those prerequisites. This honestly looks really promising, and makes me wonder if this will be the way we’ll be doing most interplanetary travel until we get fusion and/or beam propulsion going.
Starship Centurion
This is a buildable starship by 2100 AD in my opinion, it is propelled by atomic bomb pulse units in the multi-kiloton yield range, manufactured on the Moon, I would allow 74 years to construct this from lunar materials. I envision a fleet of four of these ships departing from Lunar Orbit by 2100 AD for an arrival at 2550 AD. This is a generation ship of course with a launch population of around 5 million people. One ship is populated, the other three include 2 agricultural ships and one park, the cylinders deploy in orbit around Alpha Centauri A at the optimal habitable distance, the mirrors them open up and collect natural sunlight from the star Alpha Centauri A to illuminate the interior, during cruise a light tube serves this function.
"In the Garden, a Robot Digs," by Marszha Deborah
Could two founders regenerate population-level genetic diversity instead of carrying it with them?
I had a slightly outlandish sci-fi thought:
If you were forced to start a human population from only two or few founders, could you engineer a temporary inheritance mechanism that generates diversity for the first few generations, then gradually switches itself off?
Instead of carrying a large frozen genome bank, the founders would carry something closer to a population initialization algorithm.
I expected the idea to fall apart pretty quickly, so I built a simulation and kept removing the obvious cheats.
The later experiments use:
no donor genome bank
no stored source haplotypes
no source allele-frequency table
no list of source polymorphic positions
procedurally generated founder variation
recombination and linkage
blind demographic inference against the resulting population
The interesting result is that the mechanism can repair a surprising amount of the genetic damage from an extreme two-founder bottleneck.
It does not make the bottleneck disappear. Demographic inference can still detect the scar, which is probably the result I find most reassuring.
The project also includes the failed experiments and the sequence of increasingly restrictive models, because most of the interesting work became figuring out where I was accidentally sneaking information into the system.
Repo and experiments:
https://github.com/initsixdev/founder-population-init
I’m very interested in people trying to break the premise.
Where is the biggest biological cheat still hiding?
How do you like the idea?
Tethered Ring for increased mass to space
Love this tool analyzing a tethered ring scale and layout. Whats your thoughts on the possibility of this sort of tech?
https://www.project-atlantis.com/wp-content/threejs-simulation/TetheredRing/index.html
Concept art of the “Ranger One” asteroid tug from For All Mankind season 4, by Kit Stølen
Magnetic Dyson Swarm: A Fluidic Approach to Orbital Megaengineering
drive.google.comDid he start showing his Face because Ai?
I really miss the old videos where it was just him talking and constant visuals/images about what he was talking about. Now Isaac pops up and "breaks my immersion". I cant watch the videos any more. I can only listen to audio...
Is this change due to Ai and Youtube crack down on Ai channels? Or is it just a creative change?
Is there any hope of it ever going back to the way it was?
Solution: Do a Intro and show your face. Middle of video is just Visuals about what your talking about only like it used to be. Then do a Outro and show your face. Best of both worlds.
Thank You
Humanity’s "baby steps" phase: Is modern civilization just an overconfident beginner?
Here is a thought I’ve been mulling over recently regarding the trajectory of human civilization: Modern civilization uses technology to claim total control over the environment, but in reality, we act a lot like a toddler who just learned a few words and suddenly thinks they understand how the entire world works.
If you shrink Earth’s 4.5-billion-year history down to a single 24-hour day, our cognitive awakening—our capacity for deep reflection, philosophy, and scientific thought—has only happened in the last fraction of a second. We are essentially operating "god-like" technology with a brain that evolved for the Stone Age. We resemble a brand-new driver who just got their license: mastering the basic mechanics creates a massive wave of overconfidence, which is usually right when the most critical accidents happen.
Look at how we treat the planet. From detonating nuclear bombs in space just to see what would happen, to flooding the biosphere with indestructible industrial plastics, we are constantly altering the world out of sheer blind confidence. The scariest part? Our actual understanding of Earth’s complex ecosystems is still in its absolute infancy. We barely understand the deep sea or subterranean microbiomes, yet we alter the global climate without knowing the tipping points.
We act like a child who just found a hammer, treating the entire planet as a sandbox for trial and error—without realizing that this ecosystem’s fault tolerance is likely far lower than we assume. Real maturity can only come when we hit a wall, acknowledge our strict limits, and develop genuine respect for unknown risks. Surviving over the long haul isn't about blind expansion; it's about using deep rational thought to actively fight entropy and build a resilient network that can withstand systemic crises.
Are we sitting right in that dangerous, overconfident "rookie phase"? Is this arrogant trial-and-error just an inevitable rite of passage toward maturity, or are we actively driving ourselves off a cliff? I'd love to hear your perspectives on this.
A south-pole lunar outpost on real de Gerlache terrain (real cold-trap siting, correct polar lighting) - What would you change to make it actually work?
This is Concept 001 from a project I've been building (FarsideLab): a crewed base at de Gerlache crater, near the Moon's south pole. I tried to keep it grounded rather than sci-fi - the terrain is real NASA LOLA elevation data at true scale, the lighting is path-traced at the correct low polar sun angles, and the siting is deliberate: right by the permanently shadowed cold traps that may hold water ice. The landers are based on published designs (Blue Origin Mk2, SpaceX HLS); the habitat, power and ISRU pieces are my own plausible interpretation, not an official plan.
What I'd like this sub's take on is the engineering - especially the hard parts:
- Power: some of the high ground here gets near-continuous sunlight while the crater floors stay permanently dark. Do you lean fully on solar on the peaks, or is nuclear unavoidable for riding through the outages?
- Water / ISRU: extracting ice from a permanently shadowed floor (tens of kelvin, never any sunlight) is brutal. Is in-situ extraction worth it early, or do you haul water until the base is big enough to justify the plant?
- The rim-vs-floor tension: power and comms want the lit high ground; the ice wants the dark floor. How would you actually lay a base across that gradient?
- What's the credible path from a first outpost like this to something self-sustaining - and what's the real bottleneck (power, mass to the surface, people, or closed-loop life support)?
Genuinely keen to be corrected where I've got it wrong.
Full technical breakdown - the real-data pipeline, the siting rationale, and an interactive version you can fly around in the browser - is here: https://farsidelab.com/concept/?id=moon-base
Space Habitats: The Strangest Worlds We Could Build
Build a world small enough to circle in a day—or vast enough to house a galaxy. This grand tour explores the strangest space habitats possible under known physics.
Would reward hacking "shut down" a brain?
So me and my friend u/the_syner believe in basically the Hedonistic Imperative by David Pearce but I wanted to take it a step further and not just eliminate suffering but maximize pleasure, like really maximize it. But I don't want just drugged out bliss, I want every deep form of fulfillment and having all needs met, and simulations of every pleasure inducing experience and every deep intellectual pleasure imaginable.
So I found the idea of "reward hacking" where a being like an AI figures out how to set its reward function to maximum. Now according to my friend this kills the being as it has no goals and even the micro decisions needed for neurons to fire cannot be made with no reward system, but I insist that electricity must keep flowing through their head and thus consciousness is generated, they're totally useless except as a consciousness generator. I had this idea in the context of orgasmium (making a material designed for bliss though usually characterized as only human level) and omegapoint which could make a mind capable of feeling all that deep stuff on a scale unimaginable to us, as the end stage of any civilization and they all converge on it (not realistic but assuming these things can be converged on like a convergent ideology, it's kinda a sociological clarketech).
So, there's some options to keep the mind runninng and idk why it'd reward hack if it meant death because then it would stop feeling the reward hacking. Also not sure if reward hacking gets me all my deep happiness but that could be added in and one could have things done to them instead of by them or their virtual body piloted ny AI. They could also have their neurons fired by AI systems forcefully. Now maybe you only get 99.99999% reward hacked and still retain your status as an agent, we don't know what the cut off is, how close you can get and how functional or dysfunctional such a mind would be. But even without it worst case is what people consider "suffering" will be vastly happier than our greatest highs.
Does something have to be an agent to be valuable? He thinks so but I just believe anything with consciousness is worthy of moral consideration and that agent or GI status is completely irrelevant hence why I value animals just as much as people (at least in theory, my broken human empathy still values humans higher unfortunately, one of the many things I'd change about myself with psych modding technology).
Non-physical optics for dummy powerful lasers
I've been thinking about lasers and the limits imposed by the focusing optics. I love the idea of a lens or mirror that doesn't need normal matter optics with their pesky chemical decomposition and melting/boiling points.
Metric lenses made of WIMP dark matter. Artificial gravitational lenses built from massive actively-supported matter storage structures AUs across. If we could use diffuse plasmas for this somehow that would also be pretty cool.
The goal is laser optics that can achieve the maximum theoretical beam intensities(before pair production or self-gravitation causes unavoidable divergence) without being destroyed and to a lesser extent to create lighter gargantuan optical apertures for intergalactic or even intercluster ranges. Granted it's not like i expect to ever need(or be able to practically build) lasers that can deliver 250,000 solar luminosities per square meter at a billion light years, but it would still be nice to know what the upper constraints were. I'm generally of the opinion that we can make light scalable monochromatic mirrors that can handle 1GW/m^2 but beyond that I don't know what the limits are, only that it's almost certainly not exceeding a few TW/m^2 with normal optical materials and only under the most extreme conditions even that. I want more.
Gas-giant merchant hauler IPFV Winchell Chung - Traquinniad, by Melänovis
Could we combine an NTR with a lswr for an engine that shifts gears?
A while back, a came across a comment mentioning an upgraded version of the Lithium Salt Water Rocket. It consisted of lithium deuteride pellets with a fissile shell that provided all the neutrons for fusion to occur.
Could those neutrons be provided by a solid core NTR, probably in a specialised part of the reactor to to avoid meltdown, in order to massively increase the performance of the engine?
Children of the State
I've been thinking about artificial wombs lately and the liberation of people from the arduous and potentially deadly process of pre-person (Phillip K Dick really disappointed with that one) development. Then I started thinking about artifical sperm and egg creation. If we combine these two processes then the whole reproduction thing can be totally detached from humanity save for some tissue samples. No surprise here among us SFIA fans.
But then I realized that nothing could stop states from becoming the arbiters of population. If that state is growth-oriented, then they'd have an interest in growing their domestic population. So the state voids all its "DNA is the property of the individual . . . blah blah blah" laws and just starts printing new people.
To think that the ones who initialized your birth were not two humans but the state. It made me think of Brave New World.
But then I thought, "Would this be that different from now?" How many people are born because favorable state policies caused their parents to "celebrate good times." Is it just a matter of degree? And who is to say that a state is less worthy of determining when it is best to reproduce and by how much?
Why this is relevant: these technologies are far nearer than those which will enable the construction of permanent space habitats or shellworld Earth. Modern states have almost no reluctance to misusing would-be beneficial technologies. Powerful people have noted their opposition to declining birth rates.
I think we're about to test unknown waters. What do you think?