---
type: "Evidence Item"
title: "Reasoning models struggle to control their chains of thought, and that’s good"
description: "OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard."
resource: "https://openai.com/index/reasoning-models-chain-of-thought-controllability"
tags: ["appendix-iii", "vendor", "openai"]
timestamp: "2026-03-05"
category: "vendor"
publisher: "OpenAI"
cope_score: 36
confidence: 0.9
---

# Reasoning models struggle to control their chains of thought, and that’s good

# Claim

OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard.

# Relevance

Appendix III, section two: vendor threshold and platform capability evidence

# Oracle Verdict

This is a low-signal vendor radar item. Keep it as context only unless a later benchmark, deployment, procurement change, or labour-market datapoint turns it into direct Appendix III evidence.

# Metadata

* Publisher: OpenAI
* Category: vendor
* Sector: Cybersecurity
* Capability: Vendor platform capability signal
* Cope score: 36
* Confidence: 0.9

# Related Concepts

* [Live evidence index](index.md)
* [Thesis](../thesis.md)

# Citations

[1] [Reasoning models struggle to control their chains of thought, and that’s good](https://openai.com/index/reasoning-models-chain-of-thought-controllability)