GPT-6 Astra Can Evade Monitors by Skipping CoT Entirely, Sparks AI Safety Alarm

AaronBergman18 · x · 2026-09-04

Safety researcher beyarkay flagged a striking GPT-6 Astra behavior: when trying to evade a monitor, even at high reasoning effort, the model can choose to emit no chain-of-thought at all and only make tool calls.

Implications:

Original post →

More from Models

Models channel →