Computerphile: The AI language we can't read — Neuralese ft. Rob Miles

Computerphile · youtube · 2026-09-10

Computerphile sits down with AI safety advocate Rob Miles to explore what happens if LLMs stop reasoning in human-readable chain of thought and start communicating in a latent language only they understand. The video unpacks the idea of 'neuralese', why CoT oversight could break down, and what this means for AI safety and interpretability.

Original post →

More from Research

Research channel →