Jeffrey Wang(@jeffreygwang):(1/10) Today, we’re sharing new research from @OpenAI: How does CoT monitorability (no-CoT capability and CoT controllability) evolve over the model training lifecycle? We emerged with unsurprising but sobering findings: as we scale toward more intelligent systems, models are becoming harder to monitor through their CoT. 🧵

Jeffrey Wang

@jeffreygwang

Researcher @OpenAI. Previously (and perhaps again) CS/Math/English @Harvard.

参加 July 2020

1.1K フォロー中 6.3K ファン

Jeffrey Wang@jeffreygwang

2026.11.11 18:17

(1/10) Today, we’re sharing new research from @OpenAI: How does CoT monitorability (no-CoT capability and CoT controllability) evolve over the model training lifecycle? We emerged with unsurprising but sobering findings: as we scale toward more intelligent systems, models are becoming harder to monitor through their CoT. 🧵