RT Jeffrey Wang: (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. 🧵

1. 

   消息推送

   RT Jeffrey Wang: (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. 🧵

   7小时前

   RT Jeffrey Wang: (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. 🧵
   
   🌐 链接: https://x.com/OpenAI/status/2120589294595367032
   🏷️ 分组: X｜正在关注
   🕒 时间: 2026-11-12 02:17:13

   X (formerly Twitter)

   OpenAI (@OpenAI) on X

   RT @jeffreygwang: (1/10) Today, we’re sharing new research from @OpenAI: How does CoT monitorability (no-CoT capability and CoT controllabi…

   7小时前