Anthropic says China’s GLM-5.3 nearly matches Mythos at cyber exploits

T2Covered by 1 source · first reported by TNW at 01 Oct, 12:19 UTC

GLM-5.3, an open-weight model from the Chinese lab Zhipu AI, can build working cyber exploits on its own almost as well as Claude Mythos Preview, Anthropic said on Tuesday. Its safeguards can be bypassed with simple techniques in up to 100% of tests. Anthropic’s Frontier Red Team published the…

ai

Sources

• T2Anthropic says China’s GLM-5.3 nearly matches Mythos at cyber exploitsTNW01 Oct, 12:19