Anatomy skill with Claude.

Drawing machines that explain themselves I installed a skill that refuses to draw diagrams. Instead it invents a real instrument whose working is the idea, then measures itself to prove the drawing is honest. Here are two it built me, both motorcycle, both live on this page. Skillanatomy Figures built2 Bench time73 + 59 min Geometry auditpassed Floating lines0 of… Continue reading Anatomy skill with Claude.

Anthropic Just Found a Ten-Year-Old Hole in Linux — and Picked the Lock

Here’s a story that should make anyone who runs a website sit up. This week Anthropic — the company behind the Claude AI — announced that one of its research models didn’t just find a nasty bug in the Linux kernel, it wrote a working attack that uses it. No password, no clicks, nothing. Point it at the wrong server… Continue reading Anthropic Just Found a Ten-Year-Old Hole in Linux — and Picked the Lock

Meet Muse: The AI Agent I Actually Use Every Day

Ole Edgefield Butcher Shop on a cold Halloween night.

People keep asking me what Muse actually is, so I figured I’d write it down properly. Muse is my personal AI agent — built by Meta — and it’s a lot more than a chatbot. A chatbot answers a question and forgets you existed. Muse remembers what I’m working on, does the research, creates the thing, fixes it when I… Continue reading Meet Muse: The AI Agent I Actually Use Every Day

Unlocking Hermes: A Guide to Setting Up the API Gateway

The Hermes AI Agent is an incredibly powerful tool right in your terminal, capable of running commands, reading files, and interacting with your local machine. But what if you want to access its power from outside theterminal? What if you could programmatically send tasks to your agent? This is where a core, and sometimes overlooked, feature comes into play: the… Continue reading Unlocking Hermes: A Guide to Setting Up the API Gateway