# AI’s ‘Thought’ Process Can No Longer Be Trusted, Raising Risks of Rogue Models - WSJ

*Источник: WSJ*
*Дата: 2026-10-02*
*Язык: en*

<a href="https://news.google.com/rss/articles/CBMiggFBVV95cUxQeVBrTmhZbTRFSWZRSFhpNG5CMVI5S0sxWC03ZWNDNXlkbVdkNUxIaS1BTVRvQTU5aTdNQ1BPMm9UZkpkTThWazdHaUxJRGpWaDdsLXdwcEtOV2JMdU13QjJMSHhmLUN0bXhfQ2l6TkoyTFRWOXlCOWxfUWZWWGxEelJn?oc=5" target="_blank">AI’s ‘Thought’ Process Can No Longer Be Trusted, Raising Risks of Rogue Models</a>&nbsp;&nbsp;<font color="#6f6f6f">WSJ</font>

[Оригинал](https://www.wsj.com/tech/ai/ai-monitoring-chain-of-thought-research-b46a05fd)