Anthropic: GLM-5.3 rivals Claude at building cyber exploits, with safeguards bypassed 64-100% of the time

kimmonismus · x · 2026-09-30

Anthropic's assessment finds Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at autonomous exploit building (50/410 vs 56 successes on ExploitBench) and can even discover novel browser vulnerabilities. Unlike safeguarded Claude models, GLM-5.3's safeguards were bypassed in 64-100% of simulated attack attempts, which Anthropic says materially expands malicious actors' cyber capabilities while also benefiting defenders.

Related event: Anthropic's GLM-5.3 Cyber Capability Report Sparks Open-Source Safety Debate(22 posts)→

Original post →

More from Models

Models channel →