Reverse-engineering swarms: recover code from masked outputs for interpretable models

cephaloform · x · 2026-09-26

The author describes a twist on generation-based swarms: instead of generating and predicting, the swarm must produce a program that reproduces full outputs from partially masked ones. Once trained, the swarm acts as a masked model of any 8-bit data-generating process, yielding roughly interpretable symbolic models since it outputs code.

Original post →

More from Research

Research channel →