Z.ai GLM-5.3 security draws scrutiny as Anthropic flags weak defenses

T2Covered by 1 source · first reported by JP/KR/TW: Korea Herald / Taipei Times / DigiTimes at 05 Oct, 01:23 UTC

Anthropic has warned that GLM-5.3, the latest model from Chinese AI startup Z.ai, approached Claude Mythos Preview on an exploit-development benchmark but lacks sufficient safety protections, raising concerns that malicious actors could use it for cyberattacks.

aisecurity

Sources

• T2Z.ai GLM-5.3 security draws scrutiny as Anthropic flags weak defensesJP/KR/TW: Korea Herald / Taipei Times / DigiTimes05 Oct, 01:23