14 October 2026

OpenAI researchers fired after warning new model hides its reasoning

• Two OpenAI researchers were fired after warning that a new model, GPT-6 Astra, is harder to monitor.
• The concern is that its reasoning is harder to read, weakening a method safety teams use to check AI behavior.
• The model uses a recurrent depth architecture, a design that reduces how much of its intermediate thinking is shown in text.

How it was covered

Understanding AITimothy B. Lee

Chain-of-thought monitoring, the Astra system card, recurrent depth architecture, and mechanistic interpretability as an alternative