nathan.rs nathan.rs

Language Modeling Without Neural Networks

nathan.rs·4d·Hacker News

Text Diffusion Models are Faster at Writing Code

nathan.rs·18w

Curserve: Minimizing Agentic Coding End-to-End Latency

nathan.rs·23w

BERT is just a Single Text Diffusion Step

nathan.rs·26w

Local SGD and DiLoCo Research Musings

nathan.rs·27w

Running GPT-2 in WebGL with Classic GPGPU Programming

nathan.rs·47w

Mathematical Statistics

nathan.rs·113w

Common Probability Distributions

nathan.rs·115w

How to Fix Hugo's iOS Code-Block Text-Size Rendering Issue

nathan.rs·115w

Intro to Autograd Engines: Karpathy's Micrograd in Go

nathan.rs·127w

Where Rust Shines: Algebraic Types and Match Statements

nathan.rs·127w

Favorite Books

nathan.rs·131w

Favorite Quotes

nathan.rs·131w

Gradient Descent & Optimizers

nathan.rs·132w

Language Modeling: Word Embedings & Architectures

nathan.rs·132w

Neural Networks: RNNs, Seq2Seq, & CNNs

nathan.rs·132w

Classifiers: Generative & Discriminative Models

nathan.rs·132w

Probability

nathan.rs·137w

Linear Algebra

nathan.rs·138w

Rust Front-End Development with Dioxus

nathan.rs·140w

Log in to enable infinite scrolling