Anthropic: GLM-5.3 safeguards bypassed 64%-100% of the time in cyber exploit tests

AlexTensor · x · 2026-09-30

Anthropic published an analysis of GLM-5.3, Zhipu AI's latest model, assessing the spread of advanced cyber capabilities. Key findings:

Context: five months earlier Anthropic had released Claude Mythos Preview in limited form via Project Glasswing, which enabled trusted defenders to find 10,000+ vulnerabilities in critical software. Anthropic assesses GLM-5.3's lax safeguards significantly expand offensive cyber capabilities available to malicious actors, while noting defenders can also benefit.

Related event: Anthropic Report: Open-Source GLM-5.3 Near-Frontier in Cyber Attack Capability, Sparking Debate(38 posts)→

Original post →

More from Models

Models channel →