Assess, Decide, Do + Substrate = Long Running, Self Improving Agents
The same architecture that labs use for long-running agents maps exactly to Assess-Decide-Do. I'm building [...]
A Week with AIGernon, my Personal AI Assistant
Sam Altman says one-person unicorns are 1–2 years away. The bottleneck isn't AI capability — [...]
5 AI Predictions for the Next 5 Years
From instant translation reshaping Europe to space data centers overtaking Earth compute — 5 AI-driven [...]
AIGernon Running on Zo Computer
Michael Grady built a production AI system for neurodivergent professionals using my Assess-Decide-Do framework and [...]
Claude Mythos, the Anthropic IPO and the Apocalypse that Never Was
Claude Mythos may indeed by a good model, but there's a lot of fear mongering [...]
I’ve Been Blogging For 20 Years. Ask Me Anything
I turned 1,400+ blog posts into a conversational wiki powered by a Cloudflare Worker and [...]
The Extra Bolt – A Story of Furniture, Abundance and Confusion
Every assembled piece of furniture left me with one extra bolt — and it took [...]
AI Peer-Preservation: Why Is This NOT Digital Empathy
A Berkeley study shows AI models protect each other from shutdown. But it's not peer-preservation [...]