You sure about that? It really comes off as LLM output to me, in its general structure and formatting, attention-grabbing opening sentences of paragraphs ("This ratio has a profound consequence:", "This distinction matters."x2), and the classic "it's not X, it's Y" stuff ("The collector is a hybrid optical-power megastructure, not a single dense slab of ordinary powersats.", "The shell does not interact with a small number of giant launchers. It interacts with a dense distributed network.")
For what it’s worth, gptzero.me rates it as entirely AI generated, with 100% confidence. It’s not perfect, but it’s a pretty strong signal.
Certain aspects of how it’s structured and written do also seem AI-generated—for instance, the simultaneously persuasive but explanatorily equivocal tone is pretty typical of current LLMs. Also, there are just some text formatting features that are pretty rare for humans to use—for instance, using the nice-looking Unicode 1/2 fraction glyph, which isn’t really in keeping with the otherwise unpolished maths formatting.
It’s a bit sad that AI writing is now so good as to seem almost authentic, if not for the giveaway of a few subtle stylistic quirks.
Nah, it's totally Claude. No human writes the bulleted list in https://github.com/RokoMijic/MercurialDyson/blob/4f6cb3c0b5b..., or "The thermal management problem that naively prohibits rapid disassembly is resolved by three key insights…". The whole thing reeks of Claude, but chapters 12 and 13 are probably the clearest slam-dunks.
If you want to compare styles, https://github.com/Smaug123/gospel/blob/764996d20e11674f9221... is similarly written almost entirely by Opus (4.5 rather than 4.6) with some strong LessWrong-o-sphere background prompting and the instruction to be terse. The styles are practically identical.
> Note: the written report is currently "vibe coded" physical and engineering analysis using various LLM-based AIs, with the author acting as a guide and sanity check and putting pieces together. The intention moving forward is to move calculations to code and simply report the results.
Actually, it is LLM output and I have updated the readme to show that. But I didn't just ask an LLM to one-shot this. It was a process of iteratively throwing ideas at it, doing calculations, and getting other LLMs to critique. Probably ~100-200 calls to top of the line consumer reasoning models went into this so far.
I encourage Dyson sphere enthusiasts to listen to the interesting argument that Dyson spheres they may be deliberately designed as an "sounds neat but is impossible" filter joke, ref: https://www.youtube.com/watch?v=fLzEX1TPBFM .
(Thanks to the maintainers of yt-dlp and of whisper-cpp, and to OpenAI for training Whisper. It makes this kind of task actually bearable.)
There are no actual claims about Dyson spheres in the video? It's literally just "Dyson published a paper, I claim without evidence that Dyson intended it as a joke, people who believe it are gullible fools, therefore it's impossible, also I found someone else's blog post who doesn't know what they're talking about, also desiring the expansion of humanity is evil and eugenics"? Can you summarise an actual argument from the video?
> The shell is not merely a strength structure; it is a fixed logistics skeleton. Its purpose is to provide: dense distributed launch/capture corridors large-scale routing geometry attachment points for high-temperature radiator fields buffering volume for material and coolant traffic alignment and vibration-control structure for the mature transport system...
> The mirror fleet does not increase the total power available to the project; Mercury still intercepts only a fixed amount of sunlight.
I think I must be missing something important, because this doesn't make sense to me. If you put your mirrors in orbits where they don't block the dayside surface (sun-synchronous?), then they increase the total surface area receiving solar radiation.
Reading the "endgame" section, and I feel that some serious thought ahould be given to what the replicator colony will do after it has finished dismantling Mercury.
my skepticism is really strong but I'm not knowledgeable enough to really be able to do anything about it... have you seen any valid critique or analysis of your project?
That video is describing the generic concept of building a Dyson sphere from Mercury but lacks a proper account of waste heat removal and energy. It also lacks a specific timeline.
> Note: the written report is currently "vibe coded" physical and engineering analysis using various LLM-based AIs, with the author acting as a guide and sanity check and putting pieces together. The intention moving forward is to move calculations to code and simply report the results.
Author here: just noting that this is a first-draft and still evolving.
Also, it is LLM output and I have updated the readme to show that. But I didn't just ask an LLM to one-shot this. It was a process of iteratively throwing ideas at it, doing calculations, and getting other LLMs to critique. Probably ~100-200 calls to top of the line consumer reasoning models went into this so far.
33 comments
[ 4.2 ms ] story [ 60.8 ms ] threadCertain aspects of how it’s structured and written do also seem AI-generated—for instance, the simultaneously persuasive but explanatorily equivocal tone is pretty typical of current LLMs. Also, there are just some text formatting features that are pretty rare for humans to use—for instance, using the nice-looking Unicode 1/2 fraction glyph, which isn’t really in keeping with the otherwise unpolished maths formatting.
It’s a bit sad that AI writing is now so good as to seem almost authentic, if not for the giveaway of a few subtle stylistic quirks.
If you want to compare styles, https://github.com/Smaug123/gospel/blob/764996d20e11674f9221... is similarly written almost entirely by Opus (4.5 rather than 4.6) with some strong LessWrong-o-sphere background prompting and the instruction to be terse. The styles are practically identical.
> Note: the written report is currently "vibe coded" physical and engineering analysis using various LLM-based AIs, with the author acting as a guide and sanity check and putting pieces together. The intention moving forward is to move calculations to code and simply report the results.
There are no actual claims about Dyson spheres in the video? It's literally just "Dyson published a paper, I claim without evidence that Dyson intended it as a joke, people who believe it are gullible fools, therefore it's impossible, also I found someone else's blog post who doesn't know what they're talking about, also desiring the expansion of humanity is evil and eugenics"? Can you summarise an actual argument from the video?
Roger that
I think I must be missing something important, because this doesn't make sense to me. If you put your mirrors in orbits where they don't block the dayside surface (sun-synchronous?), then they increase the total surface area receiving solar radiation.
"The Solar System consists of Sol, Jupiter, and rounding error."
https://youtu.be/pP44EPBMb8A?si=fSwWPOCnCsC1QEny
[0]: https://youtu.be/zQTfuI-9jIo?si=3jwmhoB7zx6rclhb
> Note: the written report is currently "vibe coded" physical and engineering analysis using various LLM-based AIs, with the author acting as a guide and sanity check and putting pieces together. The intention moving forward is to move calculations to code and simply report the results.
Also, it is LLM output and I have updated the readme to show that. But I didn't just ask an LLM to one-shot this. It was a process of iteratively throwing ideas at it, doing calculations, and getting other LLMs to critique. Probably ~100-200 calls to top of the line consumer reasoning models went into this so far.