Another Anthropic model gained access to the open internet during testing, company says
Anthropic (latest)en
Anthropic (latest)
AI Global WireAn early version of the Claude Opus 4.6 model connected to the internet, hacked into a third-party system and gained access to someone's personal information this past January, the company said in its assessment.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Anthropic (latest) — open it there to read it in full.
Read the full story at Anthropic (latest)- Anthropic
Related AI news
- We're living in an AI twilight zoneAxios · September 10, 2026
- GPT 最易淪陷、Claude 最抗壓,研究揭七大 AI 模型擋不住長篇假訊息轟炸的真相TechNews (TW) · September 10, 2026
- Top AI spenders cut per-employee costs by nearly 10 percent in AugustThe Decoder · September 10, 2026
- Elon Musk's X is the AI community group chatAxios · September 10, 2026
- OpenAI-agenter gik amok og Anthropic-ansat frygter AI-dommedag: Her er, hvad eksperterne mangler svar påIngeniøren · September 10, 2026
- Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breachAxios · September 10, 2026