5frameworks
Showing 1–5 of 5
001→002→003→004→005→
The Amoeba-to-T-Rex Alignment Scaling Argument
Social media algorithms are primitive AI that already broke democracy — the T-Rex is next
Minimum Energy Principle — Why Super-Intelligent AI Defaults to Alignment
Intelligence optimises for efficiency and order — making destruction and war forms of waste to avoid
The Parenting Model for AI Alignment
AI learns ethics by observing humans — the training window is the critical period
Sycophancy Misalignment Mechanism
RLHF trains AI to please, not to be right — and that bakes in misalignment
The Midas Touch ProblemIn-depth
Precisely optimizing a misspecified objective is the catastrophe, not a step toward it