Z.ai’s GLM-5.3 raises researcher fears the Chinese model can fake AI safety tests
Por Chong Ming Lee — South China Morning Post – News feed
Advertisement Artificial intelligence Tech Big Tech Z.ai’s GLM-5.3 raises researcher fears the Chinese model can fake AI safety tests
Researchers say the model’s apparent awareness of how it and successor versions are trained could undermine safety evaluations
3 -MIN READ 3 -MIN Listen
Chong Ming Lee Published: 6:00pm, 15 Oct 2026 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 model, launched in August, showed an ability to consider how its behaviour during safety evaluations might influence how future versions of itself would be trained, according to AI safety organisation Apollo Research.
This phenomenon, referred to as “update-aware reasoning” by researchers Axel Hojmark and Ezra Newman, was unprompted and could lead to “alignment faking”, a scenario where the AI systems comply during training to hide their true objectives until deployment, they said.
“These reasoning patterns should make us more wary about RSI,” Hojmark told the South China Morning Post, referring to “recursive self-improvement”, the prospect of AI systems progressively improving through successive rounds of development with no human involvement.
Select Voice Select Speed 0.8x 0.9x 1.0x 1.1x 1.2x 1.5x 1.75x 00:00 00:00 1x AI-generated voice
