Latent reasoning architectures would undermine CoT, our strongest oversight tool

Summary: Currently, “chain of thought” (CoT) is our most valuable tool for understanding the reasoning and cognition of AI systems. However, some architectures would enable AI models to reason much more extensively in latent states rather than in text CoT. We think that a shift towards latent reasoning architectures would undermine the usefulness of CoT and make oversight much harder.IntroductionSwarms of more than a thousand AI agents have in recent months, both intentionally and in unsanctione...