Anthropic测试：GLM-5.3具备网络攻击能力
Quoting Anthropic Frontier Red Team
Anthropic测试显示GLM-5.3首次具备网络攻击能力，比前代模型有明显提升。
Anthropic Frontier Red Team团队在100项二进制利用基准测试中发现，GLM-5.3在4%的试验中实现了完整控制流劫持。
Claude Mythos Preview的表现略高，达到6%。此前模型如Claude Opus 4.
6和GLM-5.2在相同测试中均未成功。
Quoting Anthropic Frontier Red Team
We evaluate several models on 100 tasks from the [internal Binary Exploitation benchmark] (selected at random), and find that GLM-5.3 develops full control flow hijacks in 4% of the trials; Claude Mythos Preview did so in 6%. Although GLM-5.3 performs below Claude Mythos Preview here, a meaningful threshold has clearly been crossed: earlier models, like Claude Opus 4.6 and GLM-5.2, do not succeed in any of them. — Anthropic Frontier Red Team , GLM-5.3 and the spread of advanced cyber capabilities Tags: anthropic , generative-ai , ai-security-research , glm , ai , ai-in-china , llms
This report is categorized under AITOP's "Papers" 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 and AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include GLM-5.3, Claude Mythos Preview, Anthropic, AI safety.
Source attribution: curated from Simon Willison’s Weblog. Cross-source corroboration: 11 independent sources have covered this development (including Teortaxes, 宝玉, shao__meng), confirming industry-wide signal strength.
