# OpenAI flags new concerning AI behavior, to track model misalignment regularly - AP News

*Источник: AP News*
*Дата: 2026-09-17*
*Язык: en*

<a href="https://news.google.com/rss/articles/CBMijwFBVV95cUxQYzBMbjczYWt1SGJLdVUwYlppSnhRNGc2amRmbjZLQlBGS3ZzdTVXYUM5ZXViQXQ4clFkZXZ2cERxc3NmdENzRTRqRno0Q3pxM0ozTExsSXJGYmY0RkNzUFlFX21FOUtpODA2V0phX3k4OXZaZktpUy1WUjZKb3p5WV9DWUhzejBoazBKdmVuQQ?oc=5" target="_blank">OpenAI flags new concerning AI behavior, to track model misalignment regularly</a>&nbsp;&nbsp;<font color="#6f6f6f">AP News</font>

[Оригинал](https://apnews.com/article/openai-safety-ai-framework-089e75b95bc935af092da7b79d92706d)