The Trinity ternary compute stack — tri CLI · BitNet LLM · VSA · GF16

Kolmogorov-Arnold Networks with discrete ternary weights {-1,0,+1}.

GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent [ICML 2026]

Generalized Lipschitz Group Equivariant Neural Networks (GLGENN) [ICML 2025]

The $SOLFUNMEME $ZOS Official Website

The meta meme

all-in-one steganography suite

The system displayed partial crystallization signatures: stable spectral entropy, marginal gradient covariance stability, and persistent purity growth. Full crystallization was not achieved within …

This HPU (Hamiltonian Process Unit) preserves the message-passing topology to ensure spectral consistency and zero-cost transferability across discretization scales. An implementation of the Grokki…

Neural Network Dirac's Physics as backend

a collection of tiny llms with usecases

Hierarchical Reasoning Model Official Release

Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

🚀 Efficient implementations for emerging model architectures

Machine-learned, GPU-accelerated particle flow reconstruction

Python implementation of the monster group

dashi based learning experiments

Numbers are fun

cant remember how this works

Simulation of cognitive entropy and perceptual resolution in subjective physics. Models functorial projection from ontological state space to perceptual representation.

Autonomous self-improving agent

An experimental framework for autonomous, self-evolving AI agents living on a server with cross-session state and persistent memory.

the monster group properties

Multi-vector latent space steering adapter module for language models

Multi-vector latent space steering adapter module for language models