New preprint asks: if interpretability is "solved," what does it mean for the science of human language?

najoungkim · x · 2026-11-19

Linguists Najoung Kim (Boston University) and Ethan Gotlieb Wilcox (Georgetown) released a preprint titled Interpretability in the Limit: How Can Understanding Machines Help us Understand Human Language? It opens with a thought experiment: suppose interpretability is fully "solved" — we can faithfully identify the representations and computations underlying any capacity in an arbitrary neural network. The paper then examines what this "interpretability in the limit" would mean for science, especially the science of human language, responding to recent discourse about automating or "solving" interpretability.

Original post →

More from Research

Research channel →