This hub covers AI software you can use today: coding assistants, tools for comparing language models side by side, and AI writing and editing tools. Each post says what I ran myself and what I only read on the vendor's public pages.
What this hub covers
AI coding assistants and how to review what they write
Tools for comparing language models side by side
AI writing, proofreading and detection tools, as those posts are published
A practical, blind-scoring method for choosing between AI models for a real feature, with a tested Node.js scorer, plus where side-by-side chat tools like Shortcut Chat help and where they stop.
Where AI-generated Solidity needs human review: tx.origin authorisation, ignored ERC-20 return values, and unchecked upgrade and access assumptions, with failing tests you can run.