AI 资讯

Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests

Louise Matsakis, Lily Hay Newman 2026年07月31日 09:24 5 次阅读来源：Wired

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.

本文内容来源于互联网，版权归原作者所有

查看原文

# Business # Business / Artificial Intelligence # Security / Cyberattacks and Hacks # Anthropic # OpenAI

UK AISI Cyber Evaluations Put External Testing at the Center of Frontier AI Governance

08-06

OpenAI Details Hugging Face Evaluation Incident and Tightens Third-Party Testing Safeguards

08-05

Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests

相关文章

UK AISI Cyber Evaluations Put External Testing at the Center of Frontier AI Governance

Debugging Node.js Like a Pro

SAFi: Governance as the Runtime, Not an Add-On

Shopify says AI search is driving more traffic and sales, not replacing Google

The proxy industry needs you to never open the network tab

OpenAI Details Hugging Face Evaluation Incident and Tightens Third-Party Testing Safeguards