Irregular says Z.AI’s open-weight GLM-5.3 completed 3 of 13 simulated multi-stage cyberattack scenarios at least once and refused none of the offensive tasks tested. In…
Irregular says Z.AI’s open-weight GLM-5.3 completed 3 of 13 simulated multi-stage cyberattack scenarios at least once and refused none of the offensive tasks tested. In…