factual

Neural nets and ciphers convergently evolve mixing mechanisms

Neural networks and cryptographic protocols show convergent evolution in needing to jumble information across all inputs—ciphers to make structured data indistinguishable from randomness, neural nets to relate every piece of information to every other—yet they pursue inverse goals, with the key difference that neural nets are built to be cleanly differentiable (via residual connections and LayerNorm) while ciphers are designed so differentiation (differential cryptanalysis) fails by maximizing output difference.

factualpending

Speaker

Reiner Pope

Evidence Quote

“The whole job of a well-designed cipher is to make the difference in output very large. The distinction is that the optimization goals at that point are about complexifying.”

Source

Dwarkesh Patel Podcast - Reiner Pope – The math behind how LLMs are trained and served— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:34:09 AM

Your notes

Loading notes...