•SiTech AI Team
Anthropic says Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at building exploits
Anthropic's Frontier Red Team says Zhipu's open-weight GLM-5.3 can build complete cyber exploits on its own, and that its safeguards can be bypassed between 64% and 100% of the time with simple techniques. The model shipped without meaningful restrictions.
