LLMs show transferable goal encodings: a Python plan replanted into C++ gets re-implemented

paul_cal · x · 2026-11-20

Arnab and Paul Calvano report signs of a 'goal encoding' in LLMs: the model plans chunks of code to be written later, abstractly enough that it can be injected into a stub in another language. They extracted this encoding from Python code, planted it into a C++ stub, and the model implemented the same algorithm in C++ with different libraries, syntax and variables — evidence of plasticity, where the LM realizes the goal through environment-appropriate pathways.

Original post →

More from Research

Research channel →