The AI Language We Can't Read: Neuralese ft. Rob Miles - Computerphile

Computerphile · 621K views · 2026 · 27:17

Open on YouTube

AI safety, AGI & impactother

Why the open web links it

Explores the concept of 'neuralese'—a potential internal language used by AI models—and its implications for AI safety and interpretability.

Linked by 19 independent sites, 2 of them widely read in the 2026-10 crawl of the open web, including sdf.org, the-decoder.com, ttrpg.network, 4d2.org, the-decoder.de.