rasbt pushes back on MIT CSAIL paper claiming harnesses won't be obsolete

rasbt · x · 2026-11-22

A new MIT CSAIL paper argues stronger LLMs will NOT make harnesses obsolete: harnesses compose model capabilities to generalize across longer, deeper and more strategic tasks while enabling more data-efficient training. Sebastian Raschka counters that the root LLM still needs a harness to make subcalls — a core open question for the long-term value of agent frameworks.

Original post →

More from coding & agent

coding & agent channel →