Chain-of-thought monitoring falls to ~5% detection when the pressure is implicit.

arXiv 2608.04735 points out that monitorability evals overwhelmingly use explicit influence, where the prompt tells the model to hide a side task, and monitors catch 60-94% across seven frontier extended-thinking models. Swap in subtle contextual bias and detection drops 41-46 percentage points in two of four settings. Add ordinary system-prompt content and it bottoms out near 5%. The behavioral influence persists the whole time. A clean CoT is not evidence of a clean trajectory. Treat CoT monitors as weak signal, never as a safety layer.