AIThe Next Webabout 2 hours ago
Anthropic: GLM-5.3 Nears Mythos Cyber Exploits
3 min read
Anthropic's Frontier Red Team reported Tuesday that Zhipu AI's open-weight GLM-5.3 builds working cyber exploits nearly matching Claude Mythos Preview, which Anthropic restricted to vetted defenders. GLM-5.3 succeeded in 50 of 410 ExploitBench attempts versus Mythos's 56, and simple tricks bypassed its safeguards in up to 100% of tests. Anyone can download it.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
