AI Researchers Debate Risks of Model-to-Model "Neuralese" Communication

AI researchers are debating whether model-to-model "neuralese" communication should be blocked. Safety researcher Bogdan Ionut Cirstea argues for prevention until interpretability matures, while repligate counters that blocking it is an illusion and only direct experiments can deliver safety.

2026-10-30 ~ 2026-10-30 · 2 related posts

• repligate vs safety researcher: trying to prevent neuralese is already lost — BogdanIonutCir2 · 2026-10-30
• repligate: fearing 'neuralese' is an illusion — direct interpretability experiments are the real path — repligate · 2026-10-30