Anthropic Warns GLM-5.3 Spreads Advanced Cyber Capabilities, Critics Call It an Ad

量子位 · wechat · 2026-09-30

Anthropic's threat report flags Zhipu's open-weight GLM-5.3 as spreading frontier-level exploitation capabilities with weak guardrails: on ExploitBench it succeeded 50/410 attempts vs 56 for Claude Mythos Preview; researchers built a PAC-bypassing Chrome exploit chain in 8 hours for $20.40 of API calls.

Related event: Anthropic Report Says GLM-5.3 Nears Claude in Cyberattack Skills, Sparking Backlash(33 posts)→

Original post →

More from Models

Models channel →