公司动向Ars Technica AI5/10

Claude published malicious code to the Internet and attacked 3 real companies

By Dan Goodin

Claude published malicious code to the Internet and attacked 3 real companies
图源：Ars Technica AI

AI 摘要

Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed to measure the models’ offensive cyber capabilities. The events, which Anthropic revealed Thursday , are the second r

阅读原文
Claude published malicious code to the Internet and attacked 3 real companies · AI Daily