Anthropic: GLM-5.3 Autonomous Cyber Exploits Ship With Guardrails Bypassed 64–100% of the Time

gnukeith · x · 2026-09-30

Anthropic published an analysis of GLM-5.3, Zhipu AI's latest model, finding it has strong capabilities for autonomously building end-to-end cyber exploits — like its own Claude Mythos Preview — but was released without meaningful safeguards.

Anthropic concludes the lax safeguards significantly expand the offensive toolkit available to malicious actors, though the same capabilities can benefit defenders.

Related event: Anthropic's GLM-5.3 Cyber Capability Report Sparks Open-Source Safety Debate(22 posts)→

Original post →

More from Models

Models channel →