Google has just launched LiteRT.js, a new library that enables machine learning models to run locally within the web browser, ...

While organizing the cables on my desk, which tend to get messy, I suddenly found myself thinking about how powerful the smartphone chips we use every day have become. The news that semiconductor ...

Over the past few months, I've been trying to replace as many of the browser extensions I use daily as possible with a local LLM. To my surprise, I've managed to replace quite a few of them while also ...

It's so small, it's just the best! Maybe I can finally find a practical use for my 4GB RAM work PC with this? This is the latest work in the LFM2.5 series that I love. It's a series I've been using ...

A curated collection of custom developer skills and prompt templates for Claude Code (Anthropic's terminal-based coding agent). These behavioral profiles and system instructions extend Claude's ...

Learn what Google’s major AI models do, including Gemini, Veo, Imagen, Nano Banana, Gemma, Lyria, Chirp, and Gemini Nano.

Tom Fenton moves from local AI concepts to hands-on tools for matching LLMs to hardware, running local chatbots with Ollama and benchmarking AI performance.

c0mpute is an inference network where the GPUs are contributed, not rented. Anyone can plug a machine in and earn for the tokens it serves; anyone can run a model through an OpenAI-compatible API ...