Mercurial Dyson – a plan for the disassembly of planet Mercury (github.com)

by indy 49 comments 58 points
Read article View on HN

49 comments

[−] uticus 42d ago

> 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...

Roger that

[−] andyjohnson0 42d ago
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.
[−] andrewflnr 42d ago

> 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.

[−] rafterydj 42d ago
This reads like an LLM plagiarizing this video from Kurzgesagt:

https://youtu.be/pP44EPBMb8A?si=fSwWPOCnCsC1QEny

[−] choilive 42d ago
Bootstrapping an electronics supply chain on another planet seems harder than building the dyson swarm itself.
[−] rmijic 41d ago
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.

[−] nacozarina 42d ago
this seems to ignore the fact that Mercury is way too deep in Sol’s gravity well to be useful, all it’s looking at is Mercury mass.
[−] throwaway270925 41d ago
From the Readme:

> 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.

[−] ossicones 42d ago
Stuff like this is why I read HN
[−] thot_experiment 42d ago
If someone can't be bothered to write it I can't be bothered to read it.
[−] LoganDark 42d ago
I am such a sucker for technical Aspie writing. I've seen it mistaken for LLM output many times but this is not that.
[−] baddash 42d ago
1-6 years can't be realistic can it? does someone have a better estimate of how long this would take?
[−] pndy 42d ago
What about orbital mechanics? Wouldn't that create issues with/for objects in the solar system?
[−] mrlonglong 42d ago
"Shellworlds". With just two shells. As described in his books by Iain M. Banks.
[−] trebligdivad 42d ago
Does Mercury not have any useful radioactive material to provide more power?
[−] jmount 42d ago
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 .
[−] alhazrod 42d ago
Please someone, send grey goo to Mercury.