Latent reasoning architectures would likely undermine CoT, our strongest oversight tool

Research question

Would latent reasoning erode the evidence available for oversight?

Design & assumptions

Technical argument distinguishes reasoning that requires a text bottleneck from voluntary verbalization.

Argument & evidence

Authors argue that more computation outside text could weaken chain-of-thought oversight.

The revised conclusion distinguishes supported claims from broader preferences.

Limits & counterevidence

Predictions depend on future architecture and capability changes; not every latent architecture increases opaque reasoning.

Source evidence

No structured numerical extraction is available in this reading package.