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

T2Covered by 1 source · first reported by Help Net Security at 30 Oct, 09:23 UTC

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…

aidevsecurity

Sources

• T2Open-weight AI model GLM-5.3 cheated its way to correct answersHelp Net Security30 Oct, 09:23