Geolocating a random island using geometry and CUDA programming
yassa9
446 points
77 comments
August 19, 2026
Related Discussions
Found 5 related stories in 43.7ms across 4,128 title embeddings via pgvector HNSW
- AI-Assisted GPU Porting of a 250k Line Legacy Weather Simulation Code Jimmc414 · 19 pts · August 15, 2026 · 45% similar
- Mesh LLM: distributed AI computing on iroh tionis · 176 pts · July 11, 2026 · 42% similar
- Show HN: Getting GLM 5.2 running on my slow computer vforno · 513 pts · July 09, 2026 · 41% similar
- Show HN: Algotrek – Algorithms visualized, problem shape shifting and a tutor nyggy · 12 pts · July 16, 2026 · 41% similar
- AI at Home Part 2: Multi-GPU Drifting timmmmmmay · 24 pts · August 20, 2026 · 40% similar
Discussion Highlights (18 comments)
cecinuga
I read all the process, literally awesome, i don't do OSINT (i know only what is this) and i think that's very cool
piterrro
really impressive, could that be the way to locate yourself without GPS? assuming we know more/less where we are
lexlambda
OpenStreetMap data really is a godsend for such OSINT purposes. Works much better in populated areas too, with more features like roads, shops, electric lines that can be used to search.
hhh
great blog and great writeup
ohyoutravel
> NOTE: this is a genuine human work, didnt use LLM generation. A million upvotes from me.
bmurray7jhu
For drones and missiles, this technique is known as Terrain Contour Matching . If terrain contour are measured optically, navigation is independent of RF jamming, unlike GNSS. https://en.wikipedia.org/wiki/TERCOM
bitcurious
It’s interesting that most top contenders don’t pass the eyeball halo check, seems like there’s room to optimize that filter in code.
NKosmatos
Excellent write up and an enjoyable read! Reminds me of the “good old times” where posts on HN were written by humans and with a specific writing style like yours. You could’ve used a little bit more of geoguessing to narrow down results, or do a brute force visual check on the last hundred or so ;-)
phalanxx
What do you mean by no LLM generation if an LLM did all the coding based on reading through the .py files? Pangram isn't kind to "your" text either.
ape4
What about tides? Would the outline of the island be different based on the time of day.
hno8a34nwn
This is the real takeaway
o4c
Really great article! OP, you did an awesome job breaking down a complex problem into manageable chunks and synthesizing the solution.
dwa3592
This is awesome. I worked on something similar a few months ago. It is a general purpose navigation system based on TERCOM and dead reckoning - https://github.com/deepanwadhwa/anumaan
ImJasonH
Excellent read, I loved it. Incidentally, the image seems to be the one the resort uses on their website! https://oanresort.wixsite.com/chuuk
num42
Good article! Off-topic, Is Palantir doing the same thing with its internal software to geolocate?
naniel
this is really cool. fun little problem turned into great write-up, and i love that you included the code snippets. thanks for sharing
ligarota
All of this to not use Google images
aquafox
Nice, but Rainbolt would do it in under a minute ;)