Episode Details

Hey! I'd love to hear your thoughts, send me a voice note.

Many advanced AI models write out their reasoning before acting, and safety teams read those notes for warning signs. Three safety researchers fired by OpenAI have published a letter urging AI companies to protect this “monitorability.” OpenAI’s own system card for GPT-6 Astra reports that the model is harder to monitor this way than its predecessor.

In this episode

• The firings, the open letter, and OpenAI’s response, including what the two sides dispute
• What chain-of-thought monitoring is, and the 2025 paper that called it “a new and fragile opportunity”
• What the GPT-6 Astra system card says about declining monitorability, and the reporting on “recurrent depth”
• Why visible reasoning matters for catching agent misbehavior
• Caveats: written reasoning was never a perfect window, and the decline was measured in OpenAI’s own tests

Bottom line: Why the researchers were fired remains disputed, but OpenAI’s own documents show its newest model is measurably harder to monitor through its reasoning. Both sides say preserving readable reasoning will take industry-wide commitments.

Sources and further reading

• Open letter from Korbak, Wang and Balesni (Oct. 2026)
• GPT-6 Astra system card, OpenAI (Sept. 3, 2026)
• Chain of Thought Monitorability position paper (July 2025)
• Gizmodo: OpenAI ousts three safety researchers (Oct. 1, 2026)
• Newsweek: the letter and OpenAI’s statement (Oct. 9, 2026)
• TechCrunch: experts on Astra’s reported reasoning technique (Sept. 2, 2026)
• Daily AI Safety: When the Evidence Can Be Edited (Oct. 8, 2026)

This post was written by Claude and fact checked by Nathan Nguyen.