Skip to main content

Posts

Cheap and cheerful LLM inference on your local network

Fast screening and costing of LLM calls using Go

Automatic redaction of personal data in the browser

Fast browser plugins with Rust and WebAssembly

Give your agents fast access to your data lake

MCP servers in Rust

Fast queries on Parquet data in Rust

Revisiting Prolog for AI

Books for understanding AI

Comparing speed of some fast languages

Looking at Zig

Local LLMs are getting easier

Advent of Code as a Lab for Fast Computing

Linear Programming in Go

Starting a New Go Project

A Basic Go Setup

Why Speed Matters