Anthropic says Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at building exploits
Anthropic published an evaluation saying Zhipu's open-weight GLM-5.3 model approaches its Claude Mythos Preview in exploit development.
Zhipu AI (GLM)
All topicsZhipu AI's GLM models: open flagship releases, coding and reasoning updates, and its business and ecosystem.
2selectedRelated topicsQwenKimi / Moonshot AIOpen source
Latest selected
1–2 of 2Sep 30
Jul 16
Security incident disclosure — July 2026
Hugging Face disclosed an intrusion detected this week against parts of its production infrastructure, driven end to end by an autonomous AI agent system. Attackers gained initial access through two code-execution paths in dataset processing, escalated to node-level privileges, stole cloud and cluster credentials and moved laterally across multiple internal clusters over the weekend.