Claudeがブラウザを自律操作する「Claude in Chrome」一般提供 プロンプトインジェクションをどう防ぐ?
ITmedia AI+ja

Anthropicは、Webブラウザの拡張機能「Claude in Chrome」を全ての有料プランで一般提供した。操作ごとの承認を求めず、AIエージェントが自律的にWebブラウザを操作する。実行の前に安全性分類器が各操作を検証する。
This is a short summary published by AI Global Wire. The full article is owned and hosted by ITmedia AI+ — open it there to read it in full.
Read the full story at ITmedia AI+- Anthropic
Related AI news
- AMD pushes ROCm for agentic workloads while Intel holds on to OpenVINODIGITIMES · September 24, 2026
- OpenAI and Anthropic bosses push UN for global terms on AIBBC Technology · September 23, 2026
- Anthropic says its biology lab has already found something bigTechCrunch AI · September 23, 2026
- Sam Altman and Dario Amodei tell the UN Security Council that governments and industry should coordinate on AI safety standards and critical decisions (Bloomberg)Techmeme · September 23, 2026
- OpenAI and Anthropic’s CEOs just delivered this message to the U.N. as AI fears swirlMarketWatch Tech · September 23, 2026
- AI-toppar i FN: Krävs globalt säkerhetssamarbeteSVT Nyheter · September 23, 2026