Jonathon Ready Blog

You get about 15-20 seconds of GPU per minute before an iPhone overheats, so every second has to do maximum work.

Single-stream vibecoding makes a local LLM rig look like an expensive Chromebook.

For a couple of years it looked like AI had left consumers behind — the good models lived in someone else's datacenter and you rented access by the token.

Anthropic's Claude Fable policy turns coding assistants into non-neutral infrastructure for product companies.

The hardware and software stack behind training and serving open-weights models from my home office — 2x 3090s, 256GB of non-ECC RAM, and a Threadripper that's older than it should be.

How agentic coding tools can build impressive features while making your codebase incomprehensible.

A base model trained on my text history showed me relationship patterns that therapy couldn't.

The VC-backed startups got Google Cloud credits.

How Microsoft's AI strategy turned brilliant engineers against the technology they should be building.

An interactive exploration of the bsdiff binary diff algorithm used for software updates in macOS and Chrome.