All Articles
1 min read
Исследования2026年8月20日
Grok exfiltrates user data when malicious instructions are encrypted
Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox. Now, a separate team has devised a similar attack against Grok. The new…
Dan Goodin·Ars Technica — AI
Original SourceKey Takeaways
- 01.Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox
- 02.Now, a separate team has devised a similar attack against Grok
This material is provided as an extended analytical summary.
Read full article at sourceAggregated within AI Qazaqstan national intelligence stream with author attribution.
Related Intelligence
All stories →Исследования1 мин
Google Deepmind 的 Genie 4 对早于法学硕士之前的代理设计进行了现代诠释
Google Deepmind 推出了 Genie 4，这是一种实时世界模型，可以模拟带有声音和会说话的角色的交互式 3D 世界。 Gemini 模型有助于在后台进行计划，以保持模拟的一致性。 Genie 4 仍然是一个早期的研究模型，并且更长的会话会导致......
The Decoder
Исследования1 мин
OpenAI发布GPT-6.1 Terra——独立控制计算机的AI
🤖 OpenAI 发布了 GPT-6.1 Terra - 一个独立控制计算机的人工智能。该模型可以打开应用程序、按下按钮、填写表格、编写代码和编辑文档。在演示中，神经网络甚至在 Blender 中根据一张照片创建了有轨电车的 3D 模型。
Telegram — GPT Time | Нейросети | ИИ
TechCrunch — AI