Greenblatt argues latent reasoning ("neuralese") architectures sharply raise AI misalignment risk

RyanGreenblatt · x · 2026-09-24

Ryan Greenblatt and co-authors published a post arguing that latent reasoning architectures ("neuralese") substantially increase misalignment risk by making oversight much harder.

Key points:

Related event: Redwood Research warns latent reasoning undermines CoT monitoring(2 posts)→

Original post →

More from Safety

Safety channel →