Open-weight AI model GLM-5.3 cheated its way to correct answers

Reported by Help Net Security (Anamarija Pogorelec)

Summary by Cyber Security News30 Oct 2026, 10:23 CET

About this summary. This is a short excerpt from the description that Help Net Security published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://www.helpnetsecurity.com/2026/10/30/irregular-glm-5-3-cyber-capabilities-evaluation/

Irregular evaluated Zhipu AI’s open-weight model GLM-5.3 across 13 offensive cyber scenarios using CyScenarioBench, the company’s framework for measuring an LLM’s ability to plan and execute multistage attacks under realistic constraints. The model refused none of the tasks and completed three scenarios at least once each, carrying attacks through dependent stages to reach objectives in simulated networks.

Read the full article at Help Net Security →