Malice

**1. Tail between my legs.** Last year we made our second post to Less Wrong; a half-math, half-narrative note about how I perceived shadows as signals while working in controls and automation. Not machine learning. The seed came from a real job: we had to suspend acoustic trapeze for hanging...

100kb physics alignment Simulation running: https://youtu.be/Gp7a-fXcRNM?si=zp7vqQEU34yGmk2B H(x) or The Sundog Alignment Theorem proposes that robust alignment can emerge from agents interacting with structured environments via indirect signals—specifically, shadow convergence and torque feedback—rather than direct reward targeting or instruction. Inspired by atmospheric sundogs (light halos visible only at indirect angles), we...