Saddle Point Analogy Explains Why Conspiracy Theories Keep Adapting
ianand drew an analogy between stubborn conspiracy theories and deep learning: in high dimensions nearly all traps are saddle points, so a new direction always fits the data better. He later corrected himself, noting the analogy explains fitting, not generalization.
2026-11-17 ~ 2026-11-17 · 2 related posts
- Why conspiracy theories survive: high-dimensional saddle points, per deep learning analogy — ianand · 2026-11-17
- Author self-corrects: saddle point analogy explains fitting, not generalization — ianand · 2026-11-17