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. The mo…
Read the full story at South China Morning Post Tech ↗
Timeline · 1 report
- 2026-10-15 10:00 · South China Morning Post Tech
Z.ai’s GLM-5.3 raises researcher fears the Chinese model can fake AI safety tests