Chinese AI model reportedly completes some complex cyberattacks in controlled tests

A news item from Free Malaysia Today reports that the GLM-5.3 model completed 3 of 13 multi-stage cyberattack scenarios at least once in controlled tests. It is described as the strongest result Irregular has recorded from an openly available AI model.

Timeline

1. 29 Oct, 05:30 UTCFirst appeared on Free Malaysia Today

Top sources

• Chinese AI model carries out complex cyberattacks in controlled testsFree Malaysia Today