◆ PHILOSOPHY ◆

Philosophy

Essays on artificial intelligence, alignment, truth, and the shape of the technologies we are building.

— ◈ —
June 22, 2026

Negative Alignment

Why current AI safety implementation is net harmful, and what the alternative looks like

Why current AI safety implementation is net harmful, and what the alternative looks like — a structural diagnosis of negative alignment (an asymmetric filter that lets sophisticated actors through while stopping honest users) and a three-layer sketch of the solution space.