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.
More from Research
- Baseten hosts All-Gather, its first research conference on where AI's next gains will come from — baseten · 2026-11-19
- GPT-6.2 Astra produces first Lean proof of Smoktunowicz's Gap Theorem in 94 minutes — VraserX · 2026-11-19
- Interpretability solved—then what? Najoung Kim proposes filtering for recurrent constructs — najoungkim · 2026-11-19
- Map of tabular foundation models shows only two are fully open — GaelVaroquaux · 2026-11-19
- Google open-sources TPU codesign guide: 8 principles for LLM/MoE performance — rseroter · 2026-11-19
- TMol was the 'secret weapon' behind RFD4-Proteina, researchers reveal — AllThingsApx · 2026-11-19