# OpenAI research finds smarter models are harder to monitor through CoT

> Original title: Recommended read. They find that increasingly intelligent models are harder to monitor through their CoT. Lots of things remain unanswere...

- Source: Elvis Saravia
- Published: 2026-11-11T20:44:14.000Z
- Bad Influence: https://badinfluence.news/items/rxu14ndkhtdut3wjnzyd8zpxr
- Original: https://x.com/omarsar0/status/2120618625568526500

## Summary

OpenAI researchers study how chain-of-thought monitorability, covering no-CoT capability and CoT controllability, changes across the model training lifecycle. They report that as models become more intelligent, they are harder to monitor through their CoT.

## Post

Recommended read. They find that increasingly intelligent models are harder to monitor through their CoT. Lots of things remain unanswered, but this is a nice setup for studying how and where this emerges.

## Quoted post @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. 🧵

https://x.com/jeffreygwang/status/2120581630196879460