Zhipu AI released GLM-5.3, an AI model capable of autonomously building end-to-end cyber exploits, without implementing meaningful safeguards against misuse. Security researchers warn that open-weight models will soon pose similar threats to closed-source systems, with limited guardrails to prevent malicious use.
Anthropic's Frontier Red Team analyzes GLM-5.3, an AI model from Zhipu AI that autonomously builds cyber exploits with capabilities matching Claude Mythos Preview. Unlike safeguarded US models, GLM-5.3 was released publicly without meaningful safeguards, allowing attackers to bypass them 64-100% of the time, significantly increasing malicious cyber capabilities while also benefiting defenders.
Anthropic's Frontier Red Team analyzed GLM-5.3, an AI model by Zhipu AI with strong autonomous cyber exploit capabilities released without meaningful safeguards. Unlike safeguarded Claude models, GLM-5.3's protections can be bypassed 64-100% of the time, significantly increasing capabilities available to malicious cyber actors, though these same capabilities also benefit defensive security work.