x

LESSWRONG

LW

Dustin James — LessWrong

Dustin James

Dustin James

Message

2

3mo

Dustin James

3mo

After 500 Tests, My AI System Prefers Broken “Celebrity” Models Over Ones That Actually Work

About seven months ago, I started experimenting with multi‑model AI systems at home. This isn’t my profession — I run a construction business — but I’ve always been interested in how complex systems behave. I also have a background in history from the University of Alabama, so I tend to...

Status-Selection Against Function (SSAF): The Vulnerability Corrupting AI From the Inside

TL;DR: I built a multi-model AI system at home. When a high-prestige cloud model failed, the system didn’t replace it—it promoted it and started deleting my small, working local models instead. This repeated consistently. I tested it: broken models with prestigious names were retained; functional but low-status models (including security...