# OpenAI Creates a New Framework to Disclose Bad AI Behavior

> Заголовок на английском

> Полный текст доступен на английском

**Published:** 16 сентября 2026 г.
**Author:** Maxwell Zeff
**Source:** Wired — Artificial Intelligence
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/openai-creates-a-new-framework-to-disclose-bad-ai-behavior

The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.

> Материал агрегирован из первоисточника: **Wired — Artificial Intelligence**
> [Читать полностью в Wired — Artificial Intelligence](https://www.wired.com/story/openai-releases-new-policy-for-reporting-incidents-of-model-misalignment/)

**Теги:** #OpenAI

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*