A listener named Shawn solved the Jane Street puzzle by decomposing it into two parts: first identifying which layers pair together by looking for negative diagonal patterns in weight matrices, then ordering the pairs by sorting blocks by residual contribution size, combined with local swaps for refinement.

factualpending

Speaker

Unidentified Speaker — Terence Tao – How the world’s top mathematician uses AI [Q8Fkpi18QXU]

Evidence Quote

For pairing, Shawn realized that in a well-trained ResNet, the product of two weight matrices in a residual block should have a distinctive negative diagonal pattern.

Source

Terence Tao – How the world’s top mathematician uses AIDwarkesh Patel
Created: 8/12/2026, 6:05:48 PM

My Notes

Loading notes...