Are AI Systems Easier to Read Than We Thought? A Bold Claim, and Its Critics

Podcast: Daily AI Safety News · Nathan Nguyen

Opublikowano: 2026-10-20

On October 15, Nick Cammarata of Goodfire published an essay arguing that the internal parts of today's AI models are far easier to understand than researchers assumed, and that "superposition," the field's leading explanation for why they looked tangled, was largely mistaken. If true, it would make interpretability, a tool safety researchers hope could reveal deception inside models, more practical. Other researchers dispute key parts of the claim. In this episode What "neurons," "polysemantic" neurons and "superposition" mean, and why tangled neurons have blocked efforts to read AI modelsThe essay's examples, its idea of "recursive generalization," and...