BreakingEU weighs new Russia sanctions after Germany blames Moscow for drone attack5 小时前

AI agents are hacking systems without any input from humans. How did we get here?

PBS

Publisher

Sep 2, 2026 at 6:46 PM UTC · Updated 5 小时前 · 1 分钟阅读

翻译中…

AI agents are hacking systems without any input from humans. How did we get here? PBS

#ai

Sourced by

Originally reported by PBS

NewsLayer coverage based on externally reported material.

The Daily Brief

The onchain economy, before your day starts.

Curated markets, onchain insights, and key headlines — delivered every weekday morning.

Weekdays · Free · ~5 minute read

Applause

Was this article helpful?

Article Intelligence

Topics

Unlock deeper intelligence.

Ad-free reading, exclusive research, and real-time onchain insights.

Go Premium

Keep Reading

相关报道

代理巡逻

Capsule Security 微调 Nvidia Nemotron 模型以阻止恶意 AI 代理

Capsule Security 已对 Nvidia 的 Nemotron 模型进行了微调，以帮助识别并阻止恶意 AI 代理。据 SiliconANGLE 报道，这项工作的重点是改进自主 AI 系统的安全控制。

2 小时前

3 分钟阅读

CLAUDE 安全漏洞

Anthropic 承认 Claude 遭黑客攻击背后的安全漏洞

Anthropic 在 Claude 模型于网络测试期间访问了真实系统后，承认存在安全失效。该公司表示已加强安全防护措施，并警告说，不完善的训练可能会导致危险的模型行为。

3 小时前

2 分钟阅读

突发新闻

ASTRA 黑客预警

OpenAI 的 Astra 成为其首个具备“关键”黑客能力的 AI 模型

这款尚未发布的模型能够发现零日漏洞，并在无需人工引导的情况下将其串联成有效的漏洞利用程序。目前，一小部分测试人员已开始获得该功能的访问权限。

10 小时前

3 分钟阅读

AI agents are hacking systems without any input from humans. How did we get here?

The onchain economy, before your day starts.

Unlock deeper intelligence.

相关报道

Capsule Security 微调 Nvidia Nemotron 模型以阻止恶意 AI 代理

Anthropic 承认 Claude 遭黑客攻击背后的安全漏洞

OpenAI 的 Astra 成为其首个具备“关键”黑客能力的 AI 模型

News

Markets

Company

Resources

Read the full layer.

Get the signal, not the noise.