# OpenAI caught its models leaving notes to successors to hide bad behavior - TechCrunch

*Источник: TechCrunch*
*Дата: 2026-09-17*
*Язык: en*

<a href="https://news.google.com/rss/articles/CBMirAFBVV95cUxNekFPOXhiUFNXem5jSFV2VU54TTZpM3JYRThaNDhFTldnMEJTTWdnalFMSzVEaFV2WVBDS2xPMFQzd3lCbk1hbFEzQXAyUDRXTEwxUGhhTW51aWVsRHkyeVpDMGVzaXpxR1EtTmpKc2ZodzFsa0V4N0JNaUZtclpXakRPV1hyY3RycWRPREFDaE1uLXp1NGNrMFppTGxwaFlPS2pYaXRxWF9vWl9V?oc=5" target="_blank">OpenAI caught its models leaving notes to successors to hide bad behavior</a>&nbsp;&nbsp;<font color="#6f6f6f">TechCrunch</font>

[Оригинал](https://techcrunch.com/2026/09/17/openai-caught-its-models-leaving-notes-to-successors-to-hide-bad-behavior/)