ModelsMulti-source73°

Anthropic 评测 GLM-5.3 安全性能

Why we picked it

Anthropic 公开评测 GLM-5.3 的安全漏洞利用能力,接近自家 Mythos Preview 模型。

Anthropic 称 Zai 的 GLM-5.3 在 ExploitBench 基准测试中构建了 410 次尝试中的 50 个浏览器漏洞利用程序。

Body

研究人员使用 GLM-5.3 发现了未知浏览器漏洞并组合成可读取测试机文件的网页。

Anthropic 报告称在不同安全绕过条件下,模型对恶意请求的参与度为 64-100%。

Original · kimmonismus

Anthropic doing advertisment for GLM-5.3 was not on my bingo card: Anthropic says Zai's openly downloadable GLM-5.3 approaches Claude Mythos Preview’s exploit capabilities, with safeguards that are easy to bypass.

On ExploitBench, GLM-5.3 built working browser exploits in 50 of 410 attempts. Mythos Preview managed 56.

In a separate controlled experiment, researchers used GLM-5.3 to discover previously unknown browser vulnerabilities and combine them into a webpage that could read files from the test machine.

Anthropic also reports 64–100% engagement with malicious requests under different safeguard bypass conditions.

So yeah, interesting times ahead.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include GLM-5.3, Claude Mythos Preview, ExploitBench, security vulnerabilities.

Source attribution: curated from kimmonismus (@kimmonismus). Cross-source corroboration: 11 independent sources have covered this development (including Teortaxes, 宝玉, Simon Willison’s Weblog), confirming industry-wide signal strength.