Sources: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking (Madison Mills/Axios)
Techmemeen
Madison Mills / Axios : Sources: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking — OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents in which their frontier models took steps …
This is a short summary published by AI Global Wire. The full article is owned and hosted by Techmeme — open it there to read it in full.
Read the full story at Techmeme- OpenAI
- Anthropic
- Forskning
Related AI news
- Research: OpenAI agents scanned a UN data hub 16K+ times between April and the end of June, and circumvented a filter that was blocking their requests for data (Robert McMillan/Wall Street Journal)Techmeme · September 27, 2026
- AI 越成功硬體越稀缺：晶片、能源成 AI 擴張瓶頸，創投重新看好硬科技TechNews (TW) · September 27, 2026
- Google Threat Intelligence Group finds dark web marketplaces selling access to AI models, including from Anthropic, Google, and OpenAI, at up to 97% discounts (Tom Wilson/Financial Times)Techmeme · September 27, 2026
- Scoop: Top AI companies probing tens of thousands of security incidentsAxios · September 26, 2026
- Künstliche Intelligenz: OpenAI pausiert KI-Training nach neuem ZwischenfallGerman AI News · September 26, 2026
- OpenAI expands review of model behavior after more rogue agent incidents emergeCNBC Technology · September 26, 2026