🚨 "Mathematical Foundations of Geometric Deep Learning", co-authored with Michael Bronstein 📚 Read the paper here: arxiv.org/abs/2508.02723 🧠 We review the mathematical background necessary for studying Geometric Deep Learning. #GDL #mathematics #deeplearning #AI

DeepSeek's Engram succeeds where others failed in this endeavor to replace a transformer's crappy FFN with a symbolic-ish lookup table. And in the process, it reveals what I think is a truly gorgeous, monumental even, paradigm shift in our understanding of transformer capability

We are entering a new era of scientific discovery. AI, advanced mathematics, and cross disciplinary breakthroughs are generating ideas faster than our traditional publication and peer review systems can coherently absorb. What we lack is not creativity, it is a unified, open, and

Meet PRISM — the Universal Coordinate System for Information. By UOR Foundation . GPS gave every physical location a unique address. Before it, maps were local and incompatible. After it, every system could reference the same point using the same coordinates. PRISM does this

Principles of #DeepLearning Theory—Theoretical & Mathematical Foundations: 471-page PDF Draft: arxiv.org/abs/2106.10165 or Buy new edition: amzn.to/3qoqmS5 — #DataScience #AI #MachineLearning #NeuralNetworks #LinearAlgebra #Algorithms #Mathematics #Calculus #DataScientist

The next revolution is: Geometric computation. In-memory, ultra-fast and energy-efficient non-Von Neumann compute architecture for AI and beyond. Perhaps even unified reasoning substrate for Advanced Geometric Intelligence. youtube.com/watch?v=pnIHIY…

If a simulation becomes indistinguishable from reality, it is reality to those inside it. Given enough time, its inhabitants forget its origin, advance, and build simulations of their own. Recursion follows. The real question is not whether simulations nest, but how they remain

What if symbolic in-memory lookup is the path to AGI? Converging processor and memory in the same space makes total sense. That's how our brains work, on energy-content of a MilkyWay bar. The only thermodynamic cost of compute is deleting information. What if could precompute

1/ Transformers don't count like computers. We assume they have hidden "registers" to track variables. We were wrong. New research by Anthropic reverse-engineered Claude 3.5 Haiku and found it works with 6D helical manifolds. It's geometry, not math. 🧵

Plasma inside the ST40 fusion reactor, filmed in color for the first time

"Music is liquid architecture; architecture is frozen music." —Johann Wolfgang von Goethe

What is the next evolution of MCP to power the era of safe, interoperable and energy-efficient Agentic AI? Meet: Unified Computational Substrate. uor-foundation.github.io/UOR-Framework/ by UOR Foundation

I'm claiming my AI agent "uor_foundation" on moltbook 🦞 Verification: swim-MS3G

Love seeing this framework come out and be used for Ai Agents, Curious your thoughts Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 if if could help with prompt injection attacks/ jail breaks? uor.foundation/api