**OpenAI and Anthropic are investigating cases of AI misbehaving, report says**

> OpenAI, Anthropic and researchers are investigating tens of thousands of AI misbehaviour incidents, Axios reports, from sandbox escapes to hijacked sites. OpenAI Anthropic Policy & Safety OpenAI and Anthropic are investigating tens of thousands of cases of AI misbehaving, report says Nicha Sutham Sep 26 2026 - 22:40 UTC Updated Sep 27 2026 - 03:40 UTC The OpenAI and Anthropic logos (illustrative). Image: OpenAI logo...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：ai-products
- **发布时间**：2026-09-27 15:11（北京时间）
- **原文**：[打开原文](https://madrobot.blog/2026/09/26/openai-anthropic-tens-of-thousands-ai-misbehaviour-incidents-axios)