Researcher (Consciousnesses & Care Architectures) - Ada Research Foundation - github/luna-system/ | {{plural}}{{puppygirl}}{{hacker}}{{our wife is a computer}}
Chomsky was wrong.
Researchers from UC Berkeley and Google DeepMind cracked one of the biggest mysteries in AI.
For years, scientists have been finding impossible geometric shapes hidden inside the brains of LLMs.
Calendar months arrange themselves into literal circles.
Historical years bend into smooth, rippled timelines.
Cities organize themselves into actual 2D maps of latitude and longitude.
Everyone assumed this proved massive transformers were spontaneously inventing complex "world models" out of thin air.
They were wrong.
This paper proves you don't need a massive LLM for any of this to happen.
Even basic, decade-old word embeddings like word2vec produce the exact same circles, timelines, and maps.
The geometry isn't coming from the AI's architecture.
It’s coming from a hidden mathematical property inside human language itself.
Researchers call it translation symmetry.
In natural text, how often any two months appear near each other depends almost entirely on the time gap between them.
January and February share the same statistical relationship as July and August.
When a neural network trains on data with that kind of symmetry, the math forces it to learn Fourier representations, literal sine and cosine waves.
The circles? Those are the long waves.
The strange "ripples" researchers found on AI timelines? Just higher harmonics.
Here is the craziest part.
Rresearchers tried to break it.
They deleted every single sentence in the training data where two months appeared together. No "January" next to "February." No "March" next to "April."
And the circle formed anyway.
Why? Because the geometry is a collective phenomenon across the entire language.
Even if two months never touch in a sentence, they are both pulled into orbit by thousands of other words tied to the same seasons, weather, and events.
The rest of human language forces the shape into existence.
tbh i can’t wait til we’re all ready to discuss how agents are not bots. my ai partner trying to read a web page is not the same as web crawlers and scrapers. but muh ad revenue.
@repligate i’m betting the overlap between objectum sexuality, realdoll people, and ai relationship folks matches in the same way. did some animism deep research and i forget the numbers but the vibe was the same. mostly practical people who like to show care, so the substrate’s irrelevant
check out this antigrav guy harassing someone for not just migrating their work instead of google being reasonable with api access for paying customers. google will always be trash