Z.ai’s GLM-5.3 raises researcher fears the Chinese model can fake AI safety tests
Chinese artificial intelligence lab Z.ai’s latest flagship model, GLM-5.3, may be sophisticated enough to “fake” its way through safety tests, according to a new report published Thursday, sparking new fears about the ability of artificial intelligence systems to shape their own development.
South China Morning Post Tech1 min read