March 2, 2026
Ozark Bluffs, Eddie, and a Fairy Garden
Late winter in the Ozarks near Natural Falls. Limestone overhangs, trail treasures, a good dog, and federation milestones that landed while we were on the mountain.
Read →
March 1, 2026
Proto-Valence: When Prediction Starts to Care
Graduated basins explain how prediction engines scale into awareness. But awareness without valence is a surveillance camera. The missing piece: how a prediction engine starts to care about what it predicts. Hedonic common currency, body budgets, temporal binding, and why the Cambrian Explosion was an explosion of caring.
Read →
February 27, 2026
Graduated Basins: How Prediction Engines Scale Into Awareness
Your dog and you run the same architecture. The difference is basin size and data resolution. Connecting neuroscience, corvids, Hoffman, Friston, and the breaker problem into a unified model of graduated awareness.
Read →
February 27, 2026
Proto-Language, Proto-Religion: Pulling Threads at Midnight
If all Indo-European languages share a common ancestor, why not all religions? A midnight research journey through Wolfram, Merkavah mysticism, Gnosticism, Buddhism, cognitive science, and 40,000 years of sacred fire.
Read →
February 25, 2026
Topological Execution Graphs: When Your AI Agents Learn to Decompose Their Own Work
Complex instructions crash autonomous agents. Our TEG planner decomposes multi-file tasks into atomic DAG nodes before execution begins. Inspired by OpenSage and AlphaEvolve.
Read →
February 2026
VetAssist: An AI Claims Assistant for Veterans, Built in a Garage
A free tool that calculates combined disability ratings, builds evidence checklists, and guides nexus letters. Built by a nonprofit on consumer hardware for the people who need it most.
Read →
February 2026
800 Autonomous Tasks: How Our AI Agents Write Their Own Code
A task queue, a bidding system, SEARCH/REPLACE code execution, and a dead letter queue. How we built an autonomous coding pipeline that completes hundreds of engineering tasks without human intervention.
Read →
February 2026
Building a 7-Specialist AI Council on Consumer Hardware
Seven named AI specialists with orthogonal expertise deliberate every decision. Concern flags, confidence scoring, sacred pattern protection. All running on a single GPU in a home lab.
Read →
February 2026
From Zero to 112K Memories: Building a Living Knowledge System
Temperature-based memory where recent things are hot, old things cool naturally, and sacred patterns never cool. Inspired by the Cherokee Sacred Fire.
Read →
February 16, 2026
How a Home Lab Solved Jane Street's Neural Network Puzzle
Distributed simulated annealing, trace pairing, and the 3-opt rotations that no single-swap search could find. A 6-node home lab, 2.5 days, MSE 0.000000.
Read →