Neural networks and cryptographic ciphers both rely on scrambling/mixing information across inputs, but they diverge sharply in their optimization goals: ciphers are built to make small input differences produce huge, unpredictable output differences (the avalanche property, exploited by differential cryptanalysis), whereas neural nets use residual connections and LayerNorm specifically to keep gradients smooth and differentiable rather than chaotic.

Reiner Pope contrasts neural nets and ciphers as convergent-but-opposite designs: both scramble information, but ciphers are optimized to blow up small input differences (differential cryptanalysis targets this), while neural nets use residual connections and LayerNorm to keep the system smoothly differentiable for gradient descent. ✦ AI generated

Reiner Pope · Dwarkesh Podcast · 2026-04-29 · original ↗

Basically, what it says is that if you take a small difference of the input, it's quite difficult to make the difference of the output be small. 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. They don't have the same residual connections, like LayerNorms.

verbatim transcript · starts at 124:02